Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false and destructiveHint=false, and the description adds context that this is a low-level escape hatch. It does not detail side effects, authentication requirements, or failure modes beyond what annotations already signal. The mention that version_object defaults to status=1 (add) provides some behavioral nuance, but the description largely relies on annotations and schema for transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary action, followed by targeted context and an explicit alternative. Every sentence earns its place, with no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of annotations, a full output schema, and complete parameter schema descriptions, the description covers the essential context: what it does, when to use it, and what to prefer instead. It could elaborate on what 'inline planned workout' implies or the distinction from schedule_workout further, but for a low-level tool with rich structured data, it is adequately complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value by pointing to list_planned_activities_raw as the source for the raw entity/program objects, which helps callers understand the expected parameter origins. This goes slightly beyond the schema's field-level descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool adds an inline planned workout to the Coros training calendar, and distinguishes itself as a low-level escape hatch from the higher-level schedule_workout. It names the specific resource (calendar) and scope (inline planned workout), making it easy to differentiate from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use this tool (when already holding raw entity/program objects) and directs callers to prefer schedule_workout for the common case. It names the alternative tool clearly, providing strong usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states the side effect 'store the access token', which is consistent with the annotations (readOnlyHint: false). It adds context about the state change, but does not elaborate on token expiration, overwriting behavior, or prerequisites. With annotations already covering the non-read-only nature, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, tightly written sentence that is front-loaded with the action and resource. There is zero waste, and it shares the essential purpose without unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description combined with the rich schema and annotations provides a fairly complete picture for an authentication tool. The existence of an output schema covers return values, and the schema details the region-bound tokens and password hashing. However, it lacks an explicit statement that this tool must be called before other API calls, making the context slightly incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage for all three parameters, including detailed descriptions for region and password handling. The description adds no additional parameter semantics, so the baseline score of 3 applies as the schema already does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Authenticate') and the resource ('Coros Training Hub API') along with the outcome ('store the access token'). It distinguishes itself from the sibling 'authenticate_coros_mobile' by specifying the Training Hub API, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is used to authenticate before accessing other API endpoints, but it does not explicitly state when to use it versus alternatives like 'check_coros_auth' or 'authenticate_coros_mobile'. There is no explicit when/when-not guidance, only the implied context that it is the primary authentication method.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate this is a mutating (readOnlyHint=false), non-destructive action. The description adds context beyond annotations: it stores a mobile token and scopes authentication to the mobile API. This is meaningful behavioral disclosure, though it does not detail token expiration, refresh behavior, or repeated-call semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is just two sentences, with the primary purpose front-loaded in the first sentence. The second sentence provides valuable context (sleep data) without any filler or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is an authentication step, and the description explains what it does, why it is needed (sleep data), and its scoping to the mobile API. With an output schema present and annotations already covering mutation/destructiveness, the description is sufficiently complete for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema fully documents email, password, and region. The description does not add extra parameter context beyond the schema, which is acceptable given the high coverage. The baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with a specific verb and object: 'Authenticate with the Coros mobile API only and store the mobile token.' It clearly identifies the resource (mobile API) and the action (authenticate/store token), and distinguishes itself from sibling authenticate_coros by emphasizing 'mobile API only.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when this tool is needed: for sleep data (deep/light/REM/awake phases) that is only available via the mobile API. It also clarifies that the Training Hub web API does not provide this data, implying the alternative. However, it does not explicitly name the sibling tool authenticate_coros as the alternative for non-sleep data, so it stops short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes beyond the readOnlyHint annotation by clarifying that the tool calls an external Coros endpoint, returns a copy of the program with derived fields, and does not itself persist changes. It explains what is calculated (duration, distance, training load, exerciseBarChart). It does not cover auth/error behavior, but that is unnecessary given the annotations and calculation-focused purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a one-sentence summary, an informative second sentence about behavior/return value, and a practical third sentence about downstream usage. Every sentence contributes value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, the description is not required to detail return values. It sufficiently covers the operation's purpose, when to use it, what it returns, and how to chain it with a sibling tool. For a calculation helper, this is a complete picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides only an opaque 'program' object with additionalProperties true and 0% description coverage, so the description carries most of the semantic responsibility. It does convey that 'program' is a workout program with exercises and derived fields, which is useful, but it does not specify the internal structure or required fields needed to invoke the tool correctly. This is a meaningful but incomplete compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Recalculate a workout program after editing its exercises') and clearly identifies the resource (workout program). It also names the underlying API call and differentiates itself from sibling scheduling tools by specifying it computes derived fields and should be followed by update_scheduled_workout.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool ('after editing its exercises') and gives concrete downstream guidance ('Feed the returned program into update_scheduled_workout when its exercises changed'). This is strong usage direction that prevents misuse relative to the scheduling siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the readOnlyHint annotation by explaining the local TTL check, the possibility of stale tokens due to server-side revocation, and the exact implications of the returned fields. It also clearly states that the tool does not re-login or alter stored tokens, providing thorough behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately detailed but well-structured, starting with a clear statement of purpose and following with relevant caveats and details. Each sentence adds value, and the use of inline code for keys improves readability. It is not excessively verbose for the complexity involved.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's diagnostic nature and the presence of an output schema, the description provides comprehensive context: it explains the default local-only behavior, the optional server verification, the meaning of `authenticated` and `expires_in_hours`, and edge cases like revocation. This is sufficient for an agent to understand the tool's role and limitations without additional documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter `verify_with_server` is fully described in the schema with details on behavior and return keys. The tool description adds context about the default local check and what the parameter modifies, but this is largely complementary to the schema rather than adding new meaning. With 100% schema coverage, a baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Check') and clearly identifies the resource ('valid Coros access tokens') and scope ('stored locally'). It distinguishes itself from sibling authentication tools by focusing on checking local storage rather than creating or managing tokens.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for use: it's a local check that can optionally verify with the server, and it warns that a local 'authenticated' result doesn't guarantee server acceptance. It doesn't explicitly name alternative tools or say when not to use it, but the behavior is well-enough contextualized for an agent to decide when to call it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds minimal behavioral context beyond the annotations: it specifies that the deletion applies to saved workout templates from the Coros library, providing the target scope. However, the destructive nature is already disclosed via destructiveHint=true, and the description does not elaborate on consequences like irreversibility or impact on dependent schedules. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no redundant words, front-loading the action and object. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple deletion tool with one parameter, destructive annotations, and an output schema, the description is sufficient. It identifies the resource type and location, though it doesn't explicitly state how to obtain the ID (left to the parameter description). Overall, it's complete given the simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides a 100% description coverage for the single parameter (workout_id) with guidance to obtain it from list_workout_templates. The description itself adds no parameter-specific semantics, but the schema carries the full load, meeting the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete'), the target ('saved workout TEMPLATE'), and the scope ('from the Coros library'), which distinguishes it from sibling tools like save_workout_template or list_workout_templates. The verb+resource is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly conveys usage for removing a saved workout template, but it does not explicitly state when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. The schema parameter description references list_workout_templates, which provides indirect guidance, but the description itself lacks explicit usage guidelines.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds no extra behavioral context beyond the basic fetch operation, which is acceptable given the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no filler. It front-loads the action and resource effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a simple read-only fetch tool with a complete input schema and output schema present. The description is sufficient for an agent to select and invoke it correctly; no critical information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with helpful descriptions for both parameters, including the note that sport_type is required for the API call and activity_id comes from list_activities. The tool description itself adds no parameter details, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Fetch' and clearly names the resource 'detail for a single Coros activity', distinguishing it from sibling tools like list_activities. It precisely communicates what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: use this when you need details for a single activity. It does not explicitly mention alternatives or exclusions, but the purpose statement makes the use case obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotation contradiction: readOnlyHint=true is consistent with 'Show...'. The description adds context beyond the annotation by specifying the exact return format, including the db_path to the SQLite file. This clarifies the tool's local, read-only nature and gives insight into what the output contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is succinct and well-structured: a single purpose sentence followed by a clear return-value section. Every word is necessary, and the format is easily scannable for an AI agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only cache inspection tool, the description fully covers purpose and output. The output schema exists, but the description adds human-readable detail about keys and meaning. There is no missing information that would impede tool selection or invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so no parameter explanation is needed. According to the rubric, 0 parameters baseline is 4. The description provides no parameter details because there are none, which is appropriate and complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Show what data is currently stored in the local cache,' using a specific verb and resource. It clearly distinguishes itself from sibling data-retrieval tools by focusing on cache metadata rather than actual data pulls. The return-value breakdown further reinforces the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when you need to inspect cache contents. The return structure clarifies that it provides counts and date ranges, not actual records, so it is clearly a diagnostic tool. However, it does not explicitly mention alternatives or exclusion criteria, which would warrant a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description provides rich behavioral context: data is served from local SQLite cache, the uncached tail fetches from the API, and longer ranges are chunked into 12-week calls. This goes well beyond the readOnlyHint annotation and clarifies performance and caching behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences: a clear purpose statement followed by two sentences of implementation details. Each sentence earns its place, providing useful information without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and annotations indicate read-only behavior, the description fully covers the data source, range constraints, and caching behavior. There are no significant gaps for a single-parameter fetch tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage for the only parameter (weeks) is 100%, so the baseline is 3. The description adds value by explaining that the range is configurable and works even on a cold cache, giving extra confidence about parameter behavior beyond the schema's basic range description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's function: 'Retrieve nightly HRV and daily metrics from Coros' with a configurable time range. It also distinguishes itself from sibling tools like get_sleep_data by specifying 'HRV and daily metrics'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains how the cache and API are used, implying that the tool is suitable for historical data ranges. However, it does not explicitly mention when to avoid this tool or suggest alternatives, so it lacks explicit exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, and the description adds behavioral context by specifying that it returns a list with short descriptions. This goes beyond the annotation without contradicting it. No additional behavioral quirks are relevant for such a simple read-only listing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that front-loads the action and resource. Every word earns its place, with no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, zero parameters, and the presence of an output schema, the description fully covers the tool's purpose and behavior. There is no missing context for an agent to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and schema coverage is 100% (vacuously). The description provides all needed context since there is nothing to configure. Baseline 4 is appropriate for a no-parameter tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') with a clear resource ('all available Coros MCP tools') and describes the output (short description of each). It clearly distinguishes itself from the sibling data tools, which perform specific operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when you need an overview of available tools. While it doesn't explicitly state alternatives or exclusions, the tool's self-referential nature and lack of competing help tools make the usage context clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, and the description adds value by detailing the return payload (sleep stage breakdown and heart rate) and the data source distinction. It goes beyond the annotation by explaining what data is returned and the API context, though it doesn't disclose rate limits or auth requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-load the core purpose, followed by a useful note about the API source and return data. No unnecessary words or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one optional parameter and an output schema, the description explains the return data (per-night breakdown, heart rate) and the API origin. It doesn't mention auth prerequisites, but sibling tools like authenticate_coros_mobile and check_coros_auth fill that gap. The output schema handles return structure, so completeness is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for the single 'weeks' parameter, so the description doesn't need to add much. It mentions 'configurable time range' but doesn't elaborate on the weeks parameter beyond the schema. Baseline of 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Fetch') and resource ('nightly sleep data from Coros'), clearly distinguishing this tool from siblings like get_daily_metrics and list_activities. It also specifies the configurable time range, which adds scope clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies it is the tool for sleep data from Coros and notes the API source (apieu.coros.com), which helps differentiate from Training Hub web API tools. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is known. The description adds no behavioral context beyond that—no mention of pagination behavior, timezone conventions, or result interpretation. It merely repeats the date-range concept already present in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler, and the main action is front-loaded. It loses a point because it is so terse that it omits useful context, but from a conciseness standpoint it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 4 parameters, an output schema, and 25 sibling tools, a one-line description is under-specified. It doesn't clarify what categories of activities are included, how this relates to list_planned_activities, or any edge cases. The output schema addresses return values, but the tool still needs more context for correct selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover 100% of parameters with formats, defaults, and examples, so the description carries no extra burden. The phrase 'date range' adds no new meaning beyond what start_day and end_day already communicate. Baseline 3 is appropriate since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and the resource 'Coros activities' with a date range scope. It distinguishes from other list_* siblings like list_exercises, though it could be more explicit that these are completed activity records as opposed to planned activities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. Given the large number of sibling tools, including list_planned_activities and list_exercises, the description offers no exclusions or preferred context, leaving the agent to guess which list tool to invoke.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the context about sport_type=4 being strength and its use for resolving planned workout entries, but does not disclose details like pagination, ordering, or catalogue scope. This is adequate given the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose and enriched with a practical use case. Every word earns its place; no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With high schema coverage, an output schema, and annotations already providing read-only/open-world context, the description is complete for selection and invocation. It provides enough integration context without needing to describe return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides full coverage for the single parameter (sport_type) with a clear description and default. The description reinforces that sport_type=4 is Strength, adding slight value beyond the schema but no new parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'List' and identifies the resource as 'the exercise catalogue', scoped by 'sport type'. This clearly distinguishes it from sibling tools like list_activities, list_workout_templates, and list_training_plans by focusing on exercises and mentioning their role in planned workouts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states a use case: resolving strength/conditioning exercises (sport_type=4) that appear in planned workouts. This gives clear context for when to use it, though it does not explicitly mention exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only and open-world behavior, so the description does not need to repeat those. It adds 'from the Coros training calendar' as useful context, but does not disclose additional behavioral details like return format or pagination, though these are partially covered by the output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that states the action and scope with no unnecessary words. It earns its place entirely.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only list tool with two well-described parameters, an output schema, and informative annotations, the description is fully sufficient. It clearly identifies the resource and source without requiring further explanation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with start_day and end_day both described as dates in YYYYMMDD format. The description adds no extra parameter meaning beyond what the schema already provides, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists planned (scheduled) activities from the Coros training calendar, using a specific verb and resource. It distinguishes itself from general list_activities by specifying 'planned' and from list_planned_activities_raw by not mentioning raw output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving scheduled activities but does not explicitly mention alternatives or exclusions. There is no guidance on when to use this vs. list_planned_activities_raw or list_activities.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and open-world semantics. The description adds valuable context about the raw response containing specific identifiers/version fields (planId, planProgramId, idInPlan, version), which is not visible in annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three concise sentences, each earning its place: purpose, usage context, and justification. It is front-loaded with the core action and avoids any filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and annotations covering safety, the description covers the essential context: what the tool does, when to use it, and why it matters. The description is sufficiently complete for a read-only list operation with 2 parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain the start_day or end_day parameters at all. The parameter names are suggestive of a date range, but the description provides no semantic meaning beyond the schema's pattern constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List planned activities') and the distinguishing nuance ('without stripping API fields'), which differentiates it from the sibling tool list_planned_activities. It also gives a specific use case, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this before updating an existing scheduled workout' and explains why: the raw fields contain identifiers and version info required by update_scheduled_workout. This gives strong when-to-use guidance and implicitly contrasts with other list tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and openWorldHint=true, so the safety profile is known. The description adds minimal context by specifying 'in the Coros account', but it does not disclose any additional behavioral traits such as data scoping, pagination, or authentication requirements. The default status list behavior is already in the schema description, so the description itself adds little beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that immediately communicates the tool's purpose. It is front-loaded and contains no filler or redundant information, making it appropriately concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one optional parameter), the presence of an output schema, and annotations indicating a safe read operation, the description is sufficient for basic use. It does not explicitly mention how it differs from the 'raw' sibling, but the output schema and sibling names provide enough context for an agent to infer the tool's role. Slightly more detail about the distinction would make it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description covers the only parameter 'status_list' at 100%, including its default and meaning. The tool description does not add any additional parameter semantics. With full schema coverage, the baseline of 3 applies, and no extra value is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'List training plans in the Coros account' uses a specific verb and resource, clearly stating the tool's function. However, it does not differentiate from the sibling tool 'list_training_plans_raw', which likely serves a similar yet distinct purpose, so it misses the distinction requirement for a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention when to prefer this over 'list_training_plans_raw' or any other sibling, nor does it state any prerequisites or exclusions. The only contextual hint is the default parameter behavior, but that is parameter semantics, not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers safety; the description adds context by revealing the tool returns raw, unstripped fields and includes entities/programs. This goes beyond the annotation, providing behavioral differentiation from the likely stripped variant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, and has no filler. The second sentence gives practical context, making it efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema and annotations, the description sufficiently clarifies the primary use case and raw-field behavior. It could have explained the status_list parameter's effect, but the overall context is mostly complete for a listing tool with a single optional filter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not mention the 'status_list' parameter at all. The schema only provides type info (array of integers or null) and a default, leaving the meaning of status codes unexplained. The description fails to compensate for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists training plans with the specific behavior of not stripping API fields, and contrasts with the likely sibling list_training_plans. It uses a specific verb and resource with a distinguishing detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use this tool: 'when the full plan payload is needed, including entities and programs' and gives an example use case (update_scheduled_workout). While it doesn't state when not to use it, the 'use this when' phrasing implies the alternative for simpler needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses inclusion/exclusion behavior: only templates created by the save_* tools appear, not one-off scheduled workouts. It also transparently specifies the returned structure with keys like workouts and count, so the agent knows exactly what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and every subsequent sentence adds value: provenance, exclusions, and return format. It is detailed but not bloated, with no redundant phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters, an output schema present, and annotations declaring read-only/open-world behavior, the description provides all the context needed to invoke the tool correctly. It names related creation/scheduling tools, clarifies exclusions, and documents the response shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so there are no parameter semantics to explain; the baseline of 4 applies. The description instead focuses on return-value semantics, which is appropriate here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'List reusable workout templates saved in the Coros library.' It also distinguishes the tool from related siblings by clarifying that templates come from save_workout_template / save_strength_workout_template and that one-off scheduled workouts are not included.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool—listing reusable templates—and gives when-not guidance by saying one-off workouts from schedule_workout / schedule_strength_workout do NOT appear. It also points to related tools like schedule_workout_template, giving the agent clear routing context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description only restates the basic action without adding behavioral context. Although the annotations already indicate destructiveHint and openWorldHint, the description does not disclose additional details such as permanence, side effects, or whether the removal is reversible. It adds no value beyond the structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 11 words, front-loaded with the action and object. It is exceptionally concise and structured, with no filler or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the operation, the detailed input schema, and the existence of an output schema, the description is sufficiently complete. It could optionally include side-effect notes, but the core context is adequately conveyed for a destructive removal operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides complete descriptions for all three parameters (plan_id, id_in_plan, plan_program_id), covering 100% of them. The tool description adds no additional parameter semantics, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (remove), the resource (scheduled workout), and the context (Coros training calendar), distinguishing it from siblings like update_scheduled_workout and schedule_workout. It is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the usage: remove a scheduled workout. However, it does not explicitly mention when to use this tool versus alternatives such as update_scheduled_workout or add_planned_workout, nor does it provide any exclusions or prerequisites. The guidance is minimal but not misleading.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The warning 'This persists to the library indefinitely' goes beyond the annotations, disclosing a long-term side effect. It also explains the contrast with schedule_strength_workout ('leaves no library residue'), giving the agent a clear mental model of the persistence behavior. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is slightly long but every sentence earns its place: the warning, conditional usage rule, alternative tool reference, and clarification prompt are all high-signal. It is front-loaded with the core purpose and structured with clear sections.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's mutation side effect and the existence of a close sibling, the description fully covers when to use it, when not to, what to do on ambiguity, and the persistence consequences. The presence of an output schema means details about return values are not required in the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the input schema provides rich descriptions for all parameters, including detailed subsemantics for the exercises array. The tool description itself does not add parameter meaning beyond what the schema already provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb+resource+destination: 'Save a REUSABLE strength workout TEMPLATE to the Coros library.' It distinguishes this tool from schedule_strength_workout by emphasizing persistence and reuse, so the agent knows exactly what it does and how it differs from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: 'Use ONLY when the user explicitly asks to save as a template...' It names the alternative schedule_strength_workout for one-off workouts, and instructs the agent to ask the user if intent is unclear. This is exemplary usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false and destructiveHint=false, but the description goes further by disclosing that this 'persists to the library indefinitely', appears in the Coros app under Workouts, and can be synced to the watch. This adds real behavioral context beyond the annotations and does not contradict them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Although the description is longer than average, every section earns its place: purpose, persistence warning, sibling alternative, user-disambiguation prompt, and post-save outcome. The critical caveat is front-loaded with a warning symbol, and the structure is easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a high-stakes persistence operation: it explains side effects, required user intent, alternatives, and disambiguation. With a rich input schema and an output schema present, nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool description itself adds little parameter-level detail, but the input schema already provides thorough coverage of all parameters, including sport_type wire-ID mappings and intensity_type defaults. At 100% schema coverage, the baseline of 3 applies; no additional parameter semantics are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise verb and resource: 'Save a REUSABLE cycling/intervals/running workout TEMPLATE to the Coros library.' It clearly distinguishes this from one-off scheduling and names the sibling tool, schedule_workout, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool ('only when the user explicitly asks to save as a template'), when not to use it (one-off workout: use schedule_workout instead), and instructs the agent to ask the user when intent is unclear. This is exemplary routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description discloses a key behavioral trait not available from annotations: 'Does NOT save to the Coros library — leaves no template behind.' It also sets expectations for handling ambiguous user intent ('If the user's intent is unclear, ASK THEM'). Annotations already indicate this is a write operation (readOnlyHint=false) and not destructive, but the description adds crucial context about the lack of persistent template side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded with the core purpose. It uses a clear multi-paragraph format with key information in the first line, followed by usage guidance and disambiguation. Every sentence adds value, though slightly verbose with the quoted question, but this earns its place. Not overly long, but could be trimmed slightly without losing intent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (5 params, 3 required, nested exercise array) and the presence of an output schema, the description covers all essential context: the one-off nature, distinction from template-saving siblings, and clear instructions for ambiguous cases. No gaps remain for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage for all five parameters, so the baseline is 3. The description does not add additional parameter-level meaning beyond the schema; it only cross-references the exercises shape to another tool ('Same shape as save_strength_workout_template'), which is already stated in the schema. No extra semantic value is provided beyond the schema's documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's primary action: 'Schedule a ONE-OFF strength workout for a specific date.' It specifies the exact verb (schedule), resource (strength workout), and scope (one-off, specific date). It also explicitly distinguishes from sibling tools like save_strength_workout_template, eliminating ambiguity about which tool to use.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: 'Use this whenever the user wants a strength workout on a specific date and doesn't explicitly ask for a reusable template.' It provides a clear alternative for reusable templates ('use save_strength_workout_template') and instructs the agent to ask the user when intent is unclear, including a direct question template. This is exceptionally actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already convey readOnly=false and destructive=false. The description adds key behavioral context: 'Does NOT save to the Coros library — leaves no template behind,' and details sport_type wire ID rejection ('Don't pass 1 directly'). This enriches the agent's understanding beyond the structured hints, though it doesn't cover all potential side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence states the purpose, followed by concise usage boundaries and an explicit clarification prompt. Every sentence earns its place; the quoted user question is structural guidance, not fluff. The length is appropriate for the tool's decision complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the common case, the alternative path, essential behavioral notes (no template saved), parameter edge cases (sport_type internal mapping), and a decision heuristic for ambiguous intent. With an output schema present, return values need not be detailed, making this complete for the tool's context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with detailed descriptions (e.g., sport_type defaults, intensity_type defaults, happen_day format). The description adds value by cross-referencing the steps shape to save_workout_template and clarifying sport type categories align with the schema's values, which goes beyond a pure schema summary.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Schedule a ONE-OFF cycling/intervals/running workout for a specific date,' using a specific verb and resource that clearly distinguishes it from reusable-template siblings. It explicitly contrasts itself with save_workout_template, leaving no ambiguity about scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use ('whenever the user wants a workout on a specific date and doesn't explicitly ask for a reusable template'), when-not-to-use (reusable template → save_workout_template), and even an ask-if-unclear script with a direct quote. This is model guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only and destructive hints. The description adds meaningful context by clarifying this schedules an existing template (not a one-off) and points to the ID requirement. It does not discuss side effects like device sync (openWorldHint), but this is partially mitigated by annotations and output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose, then usage guidance. No redundant wording; every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema and full parameter schema coverage, the description is sufficient for correct tool selection and invocation. It provides purpose, selection criteria, and alternatives without unnecessary detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions, so the description doesn't need to explain each. The description reinforces the workout_id semantics ('previously-saved template') but adds little beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool adds an existing library workout template to the training calendar. It specifically names the resource ('library workout TEMPLATE') and action ('Add'), and distinguishes itself from one-off scheduling tools by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'only when scheduling a previously-saved template by ID'. Also provides clear alternatives: 'use the inline tools instead: schedule_workout (cycling/intervals) or schedule_strength_workout (strength)'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations, the description discloses cache side effects, incremental behavior after first sync, and timeout risks for large ranges. It also mentions the CLI alternative for backfills, which annotations do not convey. No contradiction with readOnlyHint=false or idempotentHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise: three sentences, each serving a clear purpose (what it does, post-sync behavior, usage advice). It is front-loaded with the core purpose and contains no fluff or redundant details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description covers essential behavioral context: cache population, downstream effects, timeout avoidance, and CLI alternative. For a sync tool with side effects and optional parameters, this is comprehensive and leaves no obvious gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both start_day and end_day described in detail (format, defaults, timezone). The description adds no additional parameter-level meaning beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool syncs Coros data for a date range into a local SQLite cache, using a specific verb-resource pair. It distinguishes itself from read tools like get_daily_metrics by explaining its role as a cache population step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly explains when to use this tool (before reads), what happens after first sync, and gives alternative guidance for large ranges (segmenting) and initial backfill (use CLI). This directly contrasts with sibling tools and prevents misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description only needs to add context. It does so by explaining the prerequisite data fetching and the need to recalculate derived metrics via calculate_workout_program. This adds behavioral insight beyond the structured annotations and does not contradict them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exceptionally concise: two sentences. The first states purpose, the second provides a structured workflow. No filler or redundant content. Front-loaded and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex update tool with nested objects and dependencies, the description covers the workflow, prerequisite tools, and a conditional step. The output schema exists, so return values are documented. It could mention reversible/destructive consequences, but the destructiveHint annotation covers that. Overall, it is complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers all parameters with descriptions (100% coverage), including the role of entity and program and the default behavior of version_object. The description's workflow reiterates this context but adds no new syntactic or semantic details beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Update an existing scheduled workout on the Coros training calendar.' This is a specific verb and resource, and the term 'existing' distinguishes it from creation tools like schedule_workout. The workflow references sibling tools, further clarifying its role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear workflow: fetch the day with list_planned_activities_raw, edit entity/program, and run through calculate_workout_program if exercises changed. This is explicit usage guidance with named alternatives and a condition. However, it does not explicitly state when not to use the tool or contrast it with other update/schedule tools, so the score is 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.