Nestling

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

Annotations already define the tool as non-read-only, non-idempotent, and non-destructive, so the description only adds the behavior of accepting flexible time formats. This does not contradict annotations but adds only minimal context. No safety-relevant behaviors such as side effects or error handling are disclosed beyond 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 two sentences with no waste: the first sentence states the primary action and target, and the second adds a useful note about timestamp flexibility. It is front-loaded and appropriately sized for the tool's simplicity.

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 a complete schema, output schema, and annotations, the description is sufficient for an agent to understand the tool's operation. The only minor gap is the lack of explicit note about the entry being persisted or any prerequisites, but the structured fields cover the essential details. For a simple create tool, this is highly 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%, meaning each parameter (babyId, timestamp, text, tags) has a clear description. The description's mention of flexible time formats merely echoes the timestamp parameter's existing schema description, adding no new semantic meaning. Baseline of 3 is appropriate for 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 ("Log") and identifies the resource ("diary/journal entry for a baby"), clearly distinguishing it from sibling tools like create_feed, create_nappy, and create_sleep. The title and description align perfectly to convey the tool's unique 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 (i.e., logging a diary/journal entry) but provides no explicit guidance on when to choose it over alternatives such as create_feed or create_sleep. No exclusions or alternative tools are mentioned, so the usage scenario is inferred rather than stated.

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 write operation (readOnlyHint=false). The description adds a valuable behavioral insight with 'Accepts flexible time formats', which is not covered by annotations. It does not contradict annotations, but it doesn't add other behavioral context like idempotency concerns.

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 exactly two sentences, immediately states the core purpose, and highlights a key feature. There is no fluff, repetition, or extraneous 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 rich schema (7 params, all described) and the presence of an output schema, the description is conceptually complete. It does not explain what happens upon success, but the output schema likely covers this. The only minor gap is not mentioning related list_feeds tool for context, but that is not essential.

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 descriptions cover 100% of parameters, including a highly detailed explanation of the timestamp parameter. The description's mention of 'flexible time formats' largely duplicates the schema's timestamp description, adding no new meaning beyond 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 description clearly states the action ('Log') and the resource ('a feeding entry for a baby'), making the purpose unambiguous. It also differentiates from sibling create_* tools by specifying 'feeding', which is concrete and specific.

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 logging a feed), but gives no explicit guidance about when not to use it or how it compares to alternatives like list_feeds. No exclusions or alternative tool mentions are provided.

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 non-readOnly behavior, and the description adds the useful detail that flexible time formats are accepted. However, it does not disclose other behavioral traits such as whether the created record is editable or how it interacts with related baby 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 two concise sentences that front-load the main action and include a key feature (flexible time formats). 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 simple log tool with full schema coverage and an output schema, the description is nearly complete. It clearly states the action and key input flexibility; only explicit guidance on when not to use it or how it differs from other create tools 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 input schema provides descriptions for all 4 parameters with 100% coverage, including detailed timestamp format guidance. The description's mention of 'flexible time formats' reinforces the schema but adds little beyond it.

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 ('Log') and resource ('nappy/diaper change'), which clearly distinguishes it from sibling tools like create_feed and create_sleep. The title 'Log Nappy Change' 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 purpose is so specific that usage is implied, but the description does not explicitly state when to use this tool vs alternatives or mention any exclusions. No guidance is given for cases like recurring changes or integration with other baby logs.

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 readOnly and idempotent hints (both false). The description adds 'Accepts flexible time formats,' but that is parameter-related, not behavioral. It does not disclose side effects, validation rules, or requirements like an existing baby.

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 wasted words. The purpose is front-loaded, and the second sentence is a brief but acceptable note on flexibility. Efficient and clear.

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 has annotations, an output schema, and fully documented parameters, so the description can be minimal. However, it lacks usage alternatives and any caveats, making it adequate but not thorough for 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?

Schema description coverage is 100% with detailed format lists for start and end. The description's mention of 'flexible time formats' is redundant with the schema, so it adds no new meaning. 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 specific verb ('Log') and resource ('sleep session for a baby'), clearly distinguishing it from sibling create_* tools for diary, feed, and nappy. This is immediately actionable.

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 sibling create_* tools, nor are prerequisites or exclusions mentioned. The purpose is self-evident but no explicit usage direction is given.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds no behavioral context beyond the parameter schema, such as error behavior or required permissions, making this a minimal-value 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 a single, well-structured sentence that quickly communicates the tool's purpose 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?

The tool is low-complexity with a single required parameter, a complete input schema, output schema, and strong annotations. The description is sufficient to orient the agent; no major information gaps are evident.

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 fully describes babyId as a UUID, and the description's 'by ID' adds no new semantic meaning. Given 100% schema coverage, a 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 tool's function: retrieving details for a specific baby by ID. It uses a specific verb ('get') and distinguishes the singular operation from sibling list tools like list_babies.

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 when a babyId is known, providing clear context for the tool's invocation. However, it does not explicitly reference alternatives or state when not to use it, though the singular 'by ID' nature makes the intended 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds the specific scope—data sources and tools—which is useful context. 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, front-loaded sentence that efficiently conveys purpose. 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?

For a simple discovery tool with no parameters and an output schema, the description sufficiently captures functionality. The annotations cover safety, and the output schema handles 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 tool has zero parameters, and the schema confirms this. With no parameters, description has nothing to add; baseline 4 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's function: listing available data sources and tools. It uses a specific verb 'list' and resource 'available data sources and tools', distinguishing it from sibling CRUD tools.

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 'Discovery:' prefix gives clear context that this is for exploring available capabilities. While it does not explicitly exclude alternatives or name them, the sibling tools are all entity-specific operations, making this the obvious choice for initial discovery.

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, idempotentHint, and destructiveHint, covering safety. The description adds the specific return content (email, ID) and implies an authentication requirement. It does not mention failure modes, but for a simple read-only getter this is sufficient given the annotation coverage.

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 the action verb front-loaded. It contains no filler and directly states what is returned.

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 parameterless read-only getter with an output schema present, the description fully covers the key return fields. No additional context is needed given the tool's simplicity and the annotations.

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?

There are zero parameters, so the schema provides no parameter semantics. According to the rubric, 0 parameters warrants a baseline of 4. The description meaningfully describes the return value, compensating for the absence of parameters.

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 'Get' with a clear resource 'authenticated user's profile' and explicitly lists the returned fields (email, ID). It is distinct from sibling tools like get_baby or list_feeds, which focus on baby-related entities.

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 explicit alternatives are mentioned, but the context is unambiguous: this tool retrieves the authenticated user's profile. The sibling tools all operate on baby/feed/diary data, so there is no overlap and the usage context is clear enough without exclusion statements.

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 destructiveHint=false, establishing it as a safe read operation. The description adds valuable behavioral context by specifying the access scope ('owned + shared'), which clarifies what 'has access to' means. No contradictions 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, front-loaded with the main action ('List all babies') followed by the scope clarification. Every word earns its place with 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?

For a simple list operation with no parameters and an existing output schema, the description is complete. It states the resource and access scope, and the output schema covers return value structure. There is no missing information that would prevent correct tool 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, and the input schema is empty, so there are no parameter semantics to explain. With 0 params, the baseline is 4, and the description doesn't need to add anything further.

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 purpose: 'List all babies the user has access to (owned + shared).' The verb 'list' is specific, the resource 'babies' is explicit, and the scope 'owned + shared' distinguishes it from single-baby retrieval tools like get_baby and other list tools (list_diary, list_feeds, etc.).

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 on when to use the tool: when the goal is to retrieve all accessible babies, including both owned and shared. It doesn't explicitly mention alternatives or exclusions, but the phrase 'all babies the user has access to' implies it is for collection-level retrieval, differentiating it implicitly from get_baby.

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, idempotentHint=true, and destructiveHint=false, indicating a safe read operation. The description adds the date-range scoping, but this is also evident from the schema parameters. It does not disclose additional behavioral details like pagination or result ordering, but the output schema covers return 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 a single, front-loaded sentence that states the action and resource without any redundancy. It is efficient and every word contributes to understanding the tool's purpose.

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 rich annotations, full schema coverage, and an output schema, the description is fully adequate. It does not need to explain return values because the output schema exists, and the safety profile is already declared by the annotations.

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 with detailed parameter descriptions, including the date/time format for start and end. The description's mention of 'within a date range' and 'for a baby' simply restates the schema parameters without adding new meaning. The baseline of 3 applies because 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 uses the specific verb 'List' to identify the action, and clearly specifies the resource as 'diary/journal entries' with scoping to a baby and date range. This distinguishes it from sibling list tools like list_feeds and list_sleep, which handle different resource types.

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 when to use this tool (to list diary entries for a specific baby within a date range), but it does not explicitly state when not to use it or name alternatives. However, the sibling tool list and the clear resource scope provide sufficient context for an agent to select this tool appropriately.

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, idempotentHint=true, and destructiveHint=false, so safety profile is known. Description adds scoping constraints (baby, date range, feed types) which are useful. It doesn't mention pagination or ordering, but the presence of an output schema reduces the need for return-format details.

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, front-loaded with the action and resource, and contains no filler or redundant information. It is efficient and easy to parse.

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 list operation with three required parameters, an output schema, and safe annotations, the description covers all essential aspects: what it lists, scope, and parameter context. No critical missing details.

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 with detailed descriptions for all three parameters (babyId UUID, start/end flexible date-time formats). The description's mention of 'date range' adds little new meaning since parameters already explain that. Baseline 3 is appropriate given full 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 clearly states a specific verb ('List') and resource ('feeding entries') with subtypes (breast, bottle, solids) and scope (baby, date range). This distinguishes it from sibling tools like list_sleep and list_nappies, which cover different resource types.

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?

Usage context is clear: use this tool to list feeding entries for a baby within a date range. It doesn't explicitly state when not to use it or mention alternatives, but the scope is well defined and sibling tools cover distinct domains (sleep, nappies, diary).

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the date-range constraint but does not disclose additional behavior such as ordering or pagination, which is acceptable given the 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?

The description is a single, front-loaded sentence with no redundant information. It efficiently communicates the operation 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?

With an output schema and annotations present, the description adequately covers the essential scope (what, who, when) for a simple list operation. It is complete without needing to explain return values or safety, as those are already specified.

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 with detailed descriptions for babyId, start, and end, including accepted date/time formats. The tool description does not add any further parameter meaning, so it does not exceed the schema's existing clarity.

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', the resource 'nappy/diaper entries', and the scope 'for a baby within a date range'. This specific phrasing distinguishes it from sibling list tools (list_feeds, list_sleep) by resource type.

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 choose this tool over alternatives. It does not mention any exclusions, alternatives, or context beyond its core function, leaving the agent without explicit selection criteria.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the scope 'for a baby within a date range,' which is also evident from the parameters. No additional behavioral context like pagination or ordering is provided, but this is acceptable given strong 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, front-loaded sentence of only 10 words. Every word contributes to understanding the tool's purpose, and there is no wasted or redundant text.

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 list operation with a rich input schema, an output schema present, and annotations covering side effects. The description sufficiently frames the tool; return values are appropriately left to the output schema, making it complete for its complexity.

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 detailed descriptions for babyId, start, and end, including accepted date/time formats. The description's 'within a date range' restates the start/end parameters without adding meaning beyond the schema, 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 'List sleep sessions for a baby within a date range' uses a specific verb (List), resource (sleep sessions), and scope (baby, date range), clearly distinguishing it from sibling tools like list_feeds or list_nappies.

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 does not explicitly mention when to use this tool over alternatives such as list_feeds or list_diary. The usage context is implied by the resource name 'sleep' but no explicit exclusions or alternative recommendations are provided.

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