STAS Running Coach for Claude

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

With no annotations, the description carries the transparency burden. It discloses that the server rejects stale data and that the operation returns the new authoritative editing state. While it does not detail side effects or reversibility, it covers key behavioral aspects beyond what the schema provides.

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 purpose, then a usage caution, then server behavior. Every sentence earns its place with no redundancy or wasted words.

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 one-parameter commit tool with no output schema, the description explains the purpose, preconditions, and response nature. It could specify the response fields in more detail, but it is sufficient for an agent to invoke correctly in the context of the preview workflow.

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 100% coverage for the single parameter changeId, including a description that already states it is a preview ID and must be committed only after user confirmation. The main description adds little beyond restating this, so the 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 the specific verb 'Commit' and clearly identifies the resource as a previewed goal, start, activity-link, or result change. It distinguishes this tool from its sibling preview_goal_result_change and commit_profile_section_change by specifying both the action and the target.

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 'Call only after the user explicitly confirms the exact preview from preview_goal_result_change', providing a clear precondition. It also mentions that 'The server rejects stale data', which informs the agent about the need for fresh preview IDs and when not to use the tool.

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?

Even though no annotations are provided, the description discloses important behavioral details: it updates the profile only if the section hash matches the preview, implying a permanent write with a conditional guard. It could go further by explicitly stating that the commit is irreversible, but 'commit' itself implies finalization, and the user-confirmation requirement adds safety context.

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 long, placed in descending order of importance: purpose first, then conditions, then mechanism. Every sentence earns its place with no redundant text. It is 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 low complexity (single parameter, no output schema), the description fully covers the necessary context: when to call, when not to call, the security condition, and the parameter's source. It is self-contained and leaves no critical gaps for an agent to misuse the 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?

The input schema already provides a rich description for changeId (returned by preview_profile_section_change, requires user confirmation). The tool-level description reiterates this but adds no new parameter-specific semantics. Since schema coverage is 100%, the baseline of 3 is appropriate; the description doesn't degrade it but also doesn't add extra meaning.

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: 'Commit a previously previewed rules or profile memory change.' This specifies a precise verb ('commit') and resource ('profile section change'), and it distinguishes itself from sibling tools like preview_profile_section_change and restore_profile_change by focusing on the finalization 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?

The description provides explicit usage conditions: 'Call this only after the user explicitly confirms the exact full text shown for that preview' and 'If preview returned noChange=true, do not call commit.' It also notes the hash-check condition, effectively telling when the operation will succeed or fail. This is strong when-to-use guidance without needing to mention 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?

With no annotations provided, the description fully carries the behavioral burden. It discloses dry_run write-vs-preview semantics, idempotent external_id usage, required field omissions, all-day date conventions, and the prohibition against seven-day date ranges for weekly notes.

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 dense but purposeful, opening with the core action and then adding only operationally relevant details. Every sentence provides actionable guidance, with no filler or repetition of obvious schema 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?

Despite no output schema and no annotations, the description is complete enough for correct invocation. It covers preview mode, idempotent updates, ordinary vs weekly notes, date anchoring, and required exclusions, making the tool fully usable from the description alone.

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?

Top-level schema coverage is only 50% because events lacks a property-level description, but the description compensates richly. It explains dry_run behavior, external_id format, all-day date conventions, for_week semantics, and specifically warns to omit type, moving_time, icu_training_load, and workout_doc—details not present in the schema.

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 first sentence clearly states the tool's function: 'Create or update NOTE events in Intervals.' This specific verb+resource combination distinguishes it from sibling tools like create_plan_event and delete_note_events by focusing exclusively on NOTE events.

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 usage context by requiring category=NOTE and distinguishing ordinary notes from weekly review notes via for_week. However, it does not explicitly name alternative tools such as create_plan_event or delete_note_events, so it falls slightly short of fully explicit when-not-to-use 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains side effects: dry_run semantics, server-side mapping of activity_type, inference of target, local datetime requirements, validation failure handling via error.data.issues, and the need to read back events to verify structured steps. It also reveals caveats about icu_training_load and null fitness values.

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 extremely long and dense, reading more like a manual than a tool description. It is front-loaded with the core purpose, but the extensive prose and embedded JSON example make it difficult to scan. While every sentence carries useful information, the lack of structure and repetition of the example in the schema reduce its conciseness.

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 mutation tool with no output schema and no annotations, this description is exceptionally complete. It covers prerequisites, parameter constraints, failure recovery via error paths, and post-write verification steps. It leaves virtually no operational ambiguity for the agent.

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?

Although schema coverage is 100%, the description adds substantial meaning beyond the schema: exact external_id format, workout_builder syntax rules (no '-' on repeat headers, flush-left step lines), explicit prohibition of low-level fields, and clarification of dry_run behavior. It also explains how activity_type maps to server fields and how workout_builder is treated, which is not obvious from the schema alone.

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 opening sentence 'Create or update planned WORKOUT events in Intervals' clearly states a specific verb and resource, and the emphasis on workouts distinguishes it from sibling tools like create_note_event and get_planned_events. It also explains that existing events are updated by keeping the same external_id, reinforcing its dual create/update 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 gives explicit usage instructions: use it for planned workout events, update by preserving external_id, avoid deleting the day/window for simple edits, and leverage dry_run for previews. It also specifies when workout_builder is mandatory versus optional, and warns against sending low-level Intervals fields, providing clear when-to-use and when-not-to-use 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the dry_run behavior ('false deletes, true previews only'), the destructive nature of deletion, and the compatibility alias. It also warns against unsafe deletions without proper IDs. This is strong context, though it doesn't mention irreversibility or error behavior, keeping it at a 4.

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 four sentences, front-loaded with the primary action. Every sentence provides necessary context: the target, ID formats, window deletion conditions, safety warning, and dry_run semantics. No wasted words.

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 complexity (5 parameters, no output schema, no annotations), the description covers the key operational aspects: how to delete specific notes, how to do window replacement, the dry_run requirement, and a critical safety warning. It does not detail return values or error scenarios, but those are not required and the essentials are all present.

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%, giving a baseline of 3. The description adds meaningful usage semantics: that external_ids should be used for one specific note, external_id is a compatibility alias, and oldest/newest are for full-window replacement only. This clarifies how parameters interact, adding value beyond the schema's individual parameter 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 opens with 'Delete STAS note events,' which is a specific verb+resource statement. It clearly distinguishes from the sibling tool 'delete_plan_events' by focusing on note events, and further clarifies the exact ID format with 'note:YYYY-MM-DD:<slug>'. This makes the tool's 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 provides explicit guidance on when to use specific IDs versus window deletion ('Use oldest/newest window deletion only when replacing a whole note set in that date window'), and warns against deleting user-created notes without a note: external_id. However, it does not explicitly name alternative tools, so it stops short of a perfect 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?

With no annotations, the description carries the burden of behavioral disclosure. It clearly explains dry_run semantics ('false deletes, true previews only'), the compatibility alias, and window deletion scope. While it doesn't detail irreversibility or response behavior, the provided context is strong for a delete operation.

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 four sentences, front-loaded with a clear purpose, and each subsequent sentence adds distinct, necessary guidance. No redundant or vague wording.

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 no output schema and a moderately complex tool, the description covers purpose, parameter selection, and dry_run behavior comprehensively. It omits details about return values or error handling, but for a delete tool with preview, this is nearly 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 descriptions cover 100% of parameters, but the description adds meaningful use-case semantics: external_id as a compatibility alias, external_ids for exact event IDs, and oldest/newest for full-window replacement. This goes beyond the schema's structural definitions.

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 'Delete STAS plan events,' naming a specific verb and resource. It clearly distinguishes this tool from sibling tools like delete_note_events and create_plan_event by focusing on STAS plan events and their unique id formats.

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 guidance: window deletion is only for replacing the whole STAS plan, and simple edits should use create_plan_event with the same external_id. Also differentiates external_id vs external_ids with clear use cases.

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?

With no annotations, the description discloses read-only behavior, compactness, and explicitly lists omitted data (source payloads, route coordinates, latlng, raw stream arrays). This goes beyond basic mutation status and helps set expectations for response content.

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-load the purpose and usage, then add limitations. No fluff, every clause 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 one parameter and no output schema, the description provides sufficient detail: it names the data categories included and excluded. It also covers the required prerequisite flow. No further explanation seems necessary.

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 already covers training_id's origin and requirement, achieving 100% coverage. The description reinforces the prerequisite but adds no new parameter-specific meaning, so a baseline score 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 'Load a compact read-only passport for one completed workout,' specifying the verb, resource, and scope. It distinguishes itself from siblings by focusing on detailed single-workout data and references get_trainings for ID identification.

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 instructs to first identify training_id with get_trainings, then lists detailed use cases (intervals, laps, splits, terrain, weather, efforts, segments, data quality). This provides clear when-to-use guidance and names the prerequisite tool.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'This tool does not change anything,' covering the non-mutating aspect. It also mentions the requirement of stable IDs and dataVersion for later previews, which is a useful behavioral dependency. However, it does not detail what the return payload contains, leaving some ambiguity about how the state is structured.

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, tightly packed with relevant information. It starts with the primary action and resource, then adds key dependencies and a read-only guarantee. There is no filler or repetition, 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 has no parameters, no output schema, and no annotations, the description provides the sole context. It lists all the resource categories it reads and notes its non-mutating nature, which is essential for safe invocation. However, the phrase 'bounded editing state' is slightly ambiguous, and the description could have been clearer about what 'complete' includes, but overall it offers sufficient context for a read-only getter.

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 the description need not explain parameter semantics. Per the rubric, a baseline score of 4 applies. The description adds no param-related information because there are no params to document.

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 with a specific verb ('Read') and a well-specified resource ('complete bounded editing state for general goals, calendar-linked starts, race results, standalone results, and legacy results'). This distinguishes it from sibling tools like get_activity_detail and read_profile_sections, which target other data. It also explicitly notes the tool is non-mutating, reinforcing its 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 provides clear context by stating that 'Stable public IDs and dataVersion are required for every later preview,' implying this tool should be used to obtain the editing state before previewing changes. It does not explicitly name alternatives or exclusions, but the read-only nature and prerequisite hint offer sufficient guidance for an agent.

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?

With no annotations, the description explicitly states 'This tool does not change the start, activity, or result,' providing a clear safety guarantee. It also labels the operation as 'read safe nearby activity candidates,' giving insight into its side-effect-free nature. However, it does not disclose other potential behaviors like return value format or error conditions.

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 main action, and includes a downstream usage hint plus a safety guarantee. No filler words.

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 one-parameter read tool with no output schema, the description covers the core purpose, downstream usage, and safety. It lacks explicit alternative guidance and return structure details, but the simplicity makes it reasonably 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 describes goalPublicId fully (UUID, returned by get_editable_goals_results), so coverage is 100%. The description adds minimal parameter-specific meaning, just tying the returned selectionId to previewing. Per rubric, 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 it reads safe nearby activity candidates for one exact start, with a specific verb and resource. It does not explicitly distinguish from sibling tools like get_activity_detail, but the naming and context are specific enough to infer the tool's 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?

It provides a downstream usage instruction (use the returned selectionId when previewing result_link_activity) but does not explicitly state when to use this tool over alternatives or when not to use it. Usage context is implied rather than explicit.

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?

With no annotations, the description carries the burden. It states the operation is read-only ('Read'), which is a key behavioral trait. However, it does not disclose return format, pagination, or potential errors, leaving some ambiguity about what the agent will receive.

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-loaded with the core purpose. Every word earns its place, and the usage hint is woven in 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?

For a simple two-parameter read tool, the description provides sufficient context for when to use it, but lacks details about the output shape or any edge-case behavior. Since there is no output schema and no annotations, the description could be more complete about what the agent will get back.

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 'oldest' and 'newest' parameters, only mentioning a 'date window.' The agent must infer that these parameters define the window boundaries, but the description adds no explicit semantic detail beyond the schema's format patterns.

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 reads planned events from the Intervals calendar within a date window. It uses a specific verb ('Read') and identifies the resource and scope, distinguishing it from sibling tools that create or delete plan events.

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 an explicit usage context: 'Use this before rewriting or replacing an existing STAS plan.' This tells the agent when to invoke the tool, though it does not explicitly mention when not to use it or name alternative 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?

No annotations are provided, so the description carries the full burden. It discloses size-safety, pagination behavior, that calendar context does not consume the training limit, full-mode semantics, intentional omission of kilometre splits, and report truncation 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 dense but not bloated. Every sentence adds information, with a logical flow from main purpose to modes to alternatives. Slightly long but justified given the tool's 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?

Given no output schema and no annotations, the description covers return characteristics (list, calendar context, compact summaries, truncation), pagination, and alternative tools. It is complete for the tool's complexity and the surrounding tool set.

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%, but the description adds context beyond the schema by explaining when to use full=true, how offset works with date windows, and that calendar context is only on the first page. This enriches parameter understanding.

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 it loads a bounded, chronological list of completed workouts plus calendar context. It also distinguishes from get_activity_detail by noting that tool is for one workout's splits and richer 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?

Explicitly explains default mode for indexing, when to use full=true, how to paginate with offset, and when to switch to get_activity_detail. It also covers the truncation flag and tells the agent to call get_activity_detail for the complete report.

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?

With no annotations provided, the description fully discloses behavioral traits: it includes all qualifying key sessions unless truncated, never invents recovery or interval rows, explains null recovery semantics, and clarifies that confirmedStructuredIntervals is a separate verified index. This is rich, non-obvious data 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 dense but every sentence adds value, covering content, caveats, and alternatives. It front-loads the primary use case effectively. A more structured layout could improve scannability, but there is no wasted wording.

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 minimal schema (single optional parameter) and no output schema, the description is exceptionally complete: it defines the data included, temporal bounds, absence semantics, and relationship to complementary tools. It leaves few questions unanswered.

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 one parameter 'section' with enum values, but the description never mentions it or explains how it filters the response. Schema description coverage is 0%, and the description does not compensate at all, leaving the agent to guess which section to request.

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 loads an athlete's profile, goals, rules, recent load, fitness context, and more. It explicitly says 'Start here for most conversations,' which distinguishes it from sibling tools and sets the expectation of a comprehensive summary.

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 to use this tool for most conversations and provides clear alternatives for older comparisons: 'use get_trainings with a bounded date range, then get_activity_detail for one exact workout.' It also explains when not to infer unshown measurements, giving direct usage boundaries.

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 annotations are provided, so the description carries full responsibility. It discloses boundary semantics, null versus zero, field filtering, column orientation, the meaning of complete=true, source origins, custom field handling, and units/scales, making behavioral expectations remarkably transparent.

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 long, but each sentence carries substantive information about behavior, units, interpretations, or pagination. It is front-loaded with the core read behavior, and the remaining content is necessary because there is no output schema or annotations.

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 that annotations and output schema are absent, the description covers every important context: what the response looks like, what complete=true and missingRanges mean, field scales, custom field handling, provider timestamps, and handling large responses. It is fully complete for safe and correct use.

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 already covers inclusive/exclusive date semantics and the date format. The description adds further meaningful context by explicitly defining window boundaries, missingRanges, null values, and retry behavior, going beyond simple schema 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 opens with a specific verb+resource: 'Read all locally stored Intervals.icu wellness values' and immediately scopes it to any date window. It also distinguishes this from other read tools by emphasizing local cache and no live provider request.

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 clearly states when to use it: to read locally stored wellness values with no fixed day cap and no live provider call. It gives contextual guidance about retrying suggested windows and never treating a partial window as the whole request, though it does not explicitly enumerate alternative sibling tools for comparison.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'This never saves' and describes expected preview output including calendar/activity effects. It also implies a staleness constraint by requiring the exact dataVersion. While it doesn't detail error handling or validation behavior, the key safety trait (read-only preview) is clearly disclosed.

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, each earning its place: scope, prerequisite, and required action. No filler or repetition of schema details. The description is front-loaded with the core purpose and immediately provides actionable workflow steps.

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 the tool's complexity (15 command variants and no output schema), the description provides everything an agent needs: what it does, what to load first, what to send, what to show the user, and what to do next. The note about calendar/activity effects is exactly the kind of context the schema cannot convey. The description is complete for the tool's role in the workflow.

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 already provides comprehensive descriptions for the command variants and expectedDataVersion (100% coverage). The tool description adds practical guidance about using the dataVersion returned by get_editable_goals_results and reinforces that only one exact change is allowed. This complements the schema without being redundant, though the schema already carries most parameter meaning.

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 ('Preview') and resource ('goal result change') and lists the exact entity types covered (general goal, calendar-linked start, activity pairing, race result, standalone result, legacy result). It clearly differentiates from sibling commit and get tools by emphasizing that this is a no-save preview step. The scope is unmistakable.

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 workflow instructions: always load get_editable_goals_results first, send its exact dataVersion, and show preview to the user before calling commit_goal_result_change. It names the precise prerequisite and downstream tool, leaving no ambiguity about when and how to use this tool.

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?

There are no annotations, so the description carries the burden. It states clearly 'This does not update the athlete profile,' disclosing the non-mutating nature. It also explains the preview and confirmation requirement, which is important behavioral context. However, it doesn't address auth, errors, or the exact return format.

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, each serving a distinct purpose: purpose, sibling routing, and workflow. No redundancy or filler. The description is well-structured and front-loaded.

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 strong given the complex schema; it covers the core workflow (preview, confirm, don't update) and the routing to the sibling tool. However, without an output schema, it doesn't describe the exact return value (e.g., preview ID or text) beyond implying the full text is present. Still, the explanation is sufficient for an agent to know the preview's role in the commit flow.

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 has 100% description coverage for all parameters, so the baseline is 3. The description adds minimal parameter-specific meaning; it only clarifies the section scope ('rules or profile') and directs other sections elsewhere, which the schema enum already provides. The rich field-level descriptions in the schema do 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 opens with 'Create a controlled preview for rules or profile memory,' giving a specific verb and resource. It explicitly distinguishes from sibling preview_goal_result_change by stating that goals, starts, activities, and results must use that tool, 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?

The description gives explicit routing guidance: 'Goals, starts, activities, and results must use preview_goal_result_change' and clarifies that this tool is for rules or profile. It also provides the workflow step 'Before commit, show the user the exact full text...' indicating when to use and what to do.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'This is read-only', which is crucial for an agent to know there are no side effects. It also specifies what is returned ('exact full text and hashes'). It does not mention auth or error conditions, but for a simple read-only detail endpoint this is adequate.

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, each contributing essential value: the first defines the action and output, the second gives usage constraints and confirms read-only behavior. No unnecessary words or repetition of schema details, making it tightly 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?

For a one-parameter tool with no output schema, the description tells the agent what the tool returns, where to get the parameter, and when it should be used. It lacks details on error behavior or authorization, but given the tool's simplicity and the presence of sibling context, it is nearly complete. A small gap is that it doesn't mention pagination or formatting, but that's minor.

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 already provides 100% coverage with 'Change id returned by read_profile_change_history' for the only parameter. The description adds a cross-reference to the history tool, reinforcing the parameter's source, but does not add new semantic details beyond the schema's own description. 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 opens with 'Load the exact full text and hashes for one profile-memory record', which is a specific verb, resource, and output scope. It clearly distinguishes from sibling tools like read_profile_change_history (which lists records) and restore_profile_change (which mutates), 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 states when to use this tool: 'only for details or before considering a restore', and it implies the prerequisite to first use read_profile_change_history to obtain the changeId. However, it does not explicitly name alternatives or exclusions, but the context is sufficiently clear for this narrow use case.

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?

With no annotations, the description carries the burden. It discloses that the response is compact, omits text bodies and hashes, and requires nextCursor for pagination. This gives the agent a clear model of the tool's behavior. It doesn't mention authorization or rate limits, but for a read-only listing tool, the disclosed traits are sufficient.

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, no filler, with the main purpose front-loaded. Every sentence earns its place: what it does, what's omitted, how to paginate, and where to get 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 description explains the core behavior (compact index, omitted bodies/hashes, pagination, detail tool) but does not mention that results can be filtered by status or section, despite those parameters being in the schema. With no output schema or annotations, the agent might miss filtering capabilities. Overall adequate but with clear 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 50%; limit and cursor have schema descriptions. The tool description adds meaning for 'cursor' (nextCursor) and 'section' (goals, rules, profile) but does not explain 'status' beyond its enum values. With moderate coverage, the description partially compensates but leaves status semantics ambiguous.

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 starts with 'Read a compact paginated index of goals, rules, or profile memory changes,' clearly stating the verb and resource. It distinguishes from sibling tools by explicitly directing to 'read_profile_change_detail' for exact records, and the scope (goals/rules/profile) aligns with the sibling set.

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 explicit usage guidance for pagination ('Use nextCursor for another page') and an alternative ('read_profile_change_detail for one exact record'). It does not mention when not to use preview/commit/restore tools, but these are clearly different operations; the main alternative is covered.

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 annotations are provided, so the description must carry the behavioral burden. It discloses that goals/results are excluded, the read returns hashes, and the hashes feed the preview workflow. This adds useful non-obvious context, though it could more explicitly state permission requirements or the read-only safety profile.

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 tightly written sentences with no wasted words. The first sentence states the purpose and return value; the second gives a crucial usage rule. Information is front-loaded and scannable.

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 no output schema and no parameters, the description covers what is returned (hashes), what is not included (goals/results), and how to use the result in the preview workflow. This is a complete picture for a simple read 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?

The tool has zero parameters, so the baseline is 4. The description adds context about what data is read, which is sufficient since there are no parameters to clarify.

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 'Read' and identifies the exact resources: 'controlled rules and profile memory' plus what is returned (hashes). It explicitly says goals/results are not available here, distinguishing it from sibling tools like get_editable_goals_results.

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 names get_editable_goals_results as the alternative for goals/results, and gives a concrete workflow instruction: use the returned hash as previousHash before previewing a rules/profile change. This clearly communicates when and how to use the tool relative to preview/commit 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?

With no annotations, the description carries the burden and offers meaningful context: it requires the user to confirm exact full text, blocks restoring old-format goals labels, and implies a mutation by 'restore back'. It could add more about side effects or return behavior, but the prerequisites and restrictions are well disclosed.

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 that are front-loaded with the core purpose, followed by procedural guidance and a safety requirement. Every sentence earns its place with no redundancy or fluff.

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 one-parameter tool with no output schema, the description plausibly covers the workflow (load record first), the restriction (goals old-format blocked), and the confirmation requirement. It does not describe return values or detailed failure modes, but the schema provides the key precondition, making this reasonably 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 coverage is 100% for the single changeId parameter, so the baseline is 3. The description repeats the confirmation requirement already present in the schema and adds no new semantic detail about the parameter itself.

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 it restores a committed profile, goals, or rules profile memory change to its previous text, using a specific verb and resource. It also distinguishes itself from siblings like commit_* and preview_* by focusing on the restore action.

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 instructs to first load the exact record with read_profile_change_detail, states when to call (after explicit user confirmation), and provides a when-not-to-use case for old-format goals labels, directing to rebuild a canonical goals preview instead. This gives clear context and 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?

With no annotations, the description carries the full burden and does so thoroughly. It discloses the required sections, length constraints, build-from-current-facts rule, treatment of previous strategy as contamination risk, approximate nature of phase dates, review-trigger semantics, and the critical workflow of showing the exact markdown before saving and never showing one version and saving another.

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 quite long but front-loaded with the most critical constraint (save only after explicit confirmation). It is dense and contains no filler, yet its single-paragraph structure makes it harder to scan. The content earns its place given the complexity of the tool, but formatting with bullets or sections would improve clarity.

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 high complexity, no annotations, and no output schema, the description is exceptionally complete. It covers preconditions, content requirements, exclusions, confirmation workflow, adaptation guidance, and the distinction between near-term changes and review triggers. The only omission is explicit return-value info, but for a save operation this is not critical to invoke 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 already provides exhaustive semantics for strategy_md, including length, required sections, content exclusions, and confirmation workflow. The tool description largely repeats this information, adding little new parameter-level meaning. The 'contamination risk' framing is a minor addition, but schema coverage is 100%, so 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 saves an 'athlete preparation map' only after explicit user confirmation, which is specific and distinct from sibling tools like create_plan_event or create_note_event. It explicitly differentiates the map from a calendar, weekly plan, workout prescription, or full coaching analysis.

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 explicit when-to-use guidance: save only after explicit user confirmation, only when the athlete asks for strategy/season work or explicitly agrees to a long-term route change. It also tells when not to use it (do not proactively ask to convert legacy strategies) and what not to store (session frequency, load targets, etc.).

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 annotations are provided, so the description carries the full burden. It describes the read-only nature implicitly through 'Check,' but it does not explicitly state that it has no side effects or side-effect-free behavior. The safety profile is not fully disclosed.

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 short sentences with no redundant information. The description is front-loaded with the action and includes a clear usage qualifier.

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 zero-parameter diagnostic tool with no output schema, the description is complete. It states what it does and when to use it, leaving no significant 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?

The tool has zero parameters, so the baseline score is 4. The description adds nothing beyond the schema, but none is 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 states a specific verb and resource: 'Check which STAS user is currently authenticated.' This clearly distinguishes the tool from sibling tools that deal with goals, plans, or profiles.

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 says 'Use only for diagnostics or reconnect troubleshooting,' providing explicit context on when to invoke the tool. It doesn't name alternatives because no sibling offers similar functionality, but the exclusion is clear.

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