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

The description discloses one-time use, a 10-minute expiry, the need to open the link in a browser, the fact that it reads no WHOOP data, and the alternate behavior in stdio mode. This goes well beyond the annotations and is consistent with readOnlyHint=true.

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

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

The description is front-loaded with the core result, then gives usage context, user instructions, and a caveat. Every sentence contributes necessary information 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 tool with no parameters and no output schema, the description fully covers invocation context, user action required, expected effect on other tools, and environment-specific behavior. Nothing an agent needs is missing.

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

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

The tool has zero parameters and the schema already reflects that completely, so there is nothing for the description to add. This matches the baseline for a parameter-less tool.

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

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

The description names a specific verb and resource: it returns a one-time link that connects the user's WHOOP account. It also clearly distinguishes itself from the sibling data tools by stating it doesn't read any WHOOP data.

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

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

It explicitly says when to use the tool: when a data tool reports WHOOP isn't connected or authorization has expired. It also covers the stdio-mode exception and explains the expected outcome, so the agent knows when it applies and when it doesn't.

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?

Adds substantial behavioral context beyond annotations: live fetching on every call, no caching, error handling ('if WHOOP can't be reached, it says so'), and auth requirement (asks to call get_auth_url if not connected). Also notes missing days are skipped. These details are not in annotations and materially affect how an agent interprets results. No contradiction with the readOnly/readOnlyHint 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 dense but every sentence earns its place: it front-loads the core purpose and output, then covers usage examples, alternatives, parameter guidance, and behavioral details. No fluff or repetition; it reads naturally and logically.

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?

Covers all essential aspects for a simple list tool: output format, default, range, filtering of unscored days, error handling, auth flow, and sibling routing. There is no output schema, but the description fully describes the return value. Given the low parameter count and clear annotations, nothing an agent needs to call it correctly 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?

Schema already fully documents 'days' (range and default). The description adds value by mapping typical values to real-world periods ('7 for the last week, 30 for the last month, up to 90'), which aids correct selection. Since schema coverage is 100%, baseline is 3, but the contextual mapping lifts it to 4.

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?

States a specific verb ('Returns') and resource ('daily recovery') with clear output format (Markdown table with scores, HRV, RHR). It explicitly differentiates from siblings by naming get_today and get_sleep_analysis with their use cases, so an agent can distinguish without opening other schemas.

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 tells when to use it ('for patterns and comparisons'), provides concrete examples ('how has my HRV changed this month?'), and gives when-not-to-use alternatives ('For today alone, use get_today; for the sleep behind the numbers, use get_sleep_analysis'). Also gives parameter selection guidance for days (7/30/90) matching the time window.

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 indicate read-only, open-world, idempotent, and non-destructive behavior, but the description adds valuable context beyond that: it fetches live data each call, keeps no copy, reports if WHOOP is unreachable, and instructs the user to call get_auth_url if not connected. This is exactly the kind of behavioral disclosure that helps an agent anticipate outcomes.

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 dense paragraph but every sentence carries useful information: output format, inclusions/exclusions, usage purpose, alternatives, parameter guidance, read-only nature, live fetching, error handling, and auth. It is front-loaded with the core function and remains efficient without padding. Slightly long but justifiably so.

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?

There is no output schema, but the description fully specifies the return format (Markdown table with sleep stage hours, performance %, efficiency %, and averages) and covers edge cases (naps excluded, nights without score, day attribution, connectivity errors, auth requirement). Nothing an agent needs to call this correctly 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 schema fully documents the `days` parameter (range, default, meaning), so the baseline is 3. The description adds extra value by explaining the effect of different values ('7 for the last week, 30 for the last month, up to 90') and clarifying that it counts back from today, which is not explicit in the schema. This elevates it slightly above baseline.

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 exactly what the tool does: returns nightly sleep for a specified number of days, newest first, in a Markdown table. It clearly distinguishes itself from siblings by naming get_today for last night's stages and get_recovery_trends for recovery, and it specifies the exact data included (sleep stages, performance, efficiency) and excluded (naps, unscored nights, time in bed).

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

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

It explicitly says when to use this tool ('Use it for sleep patterns') and when to use alternatives ('For last night's stages, use get_today; for the recovery those nights produced, use get_recovery_trends'). It also gives concrete guidance on setting the days parameter (7 for last week, 30 for last month, up to 90), leaving no ambiguity.

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, but the description adds valuable behavior: live fetch, no copy, error handling if WHOOP unreachable, and handling of missing connection by asking for auth. This goes beyond the annotation's minimal read-only flag.

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 longer than necessary but well-structured: core return, use case, alternatives, parameter advice, and behavioral notes. It's not tautological, and each sentence adds value, though it could be tightened slightly.

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?

Without an output schema, the description details the return format (Markdown table, averages, omitted days) and covers failure modes. Combined with annotations, an agent has everything needed to call it 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 schema already documents the `days` parameter fully, but the description adds meaningful usage semantics: '7 for the last week, 30 for the last month, up to 90' and explains the default and max. This enhances the schema information.

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?

States clearly it returns daily strain for a period, newest first, as a Markdown table with strain and calories. Explicitly distinguishes from get_workouts and get_recovery_trends, so an agent knows exactly what it does and what it doesn't.

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 usage context: 'Use it for overall load and activity trends' and names alternatives for different needs. Also gives parameter guidance on how to set days for different time spans, and notes it's read-only.

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

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

Annotations already cover read-only and idempotent safety, but the description adds substantial context: it fetches live data on every call and keeps no copy, reports a newer-version notice to pass on, explains the failure message when WHOOP is unreachable, and instructs to call get_auth_url when not connected. This is rich behavioral disclosure beyond the structured fields.

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

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

The description is front-loaded with what is returned, then usage and alternatives, then behavioral notes. Every sentence adds operational value: the return contents, sibling routing, live-fetch semantics, version notice, and connection fallback all matter to an agent deciding whether and how to call this tool.

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?

There is no output schema, so the description carries the full burden of explaining return values and does so in detail (Markdown format, exact fields included). It also covers preconditions (WHOOP connected) and failure behavior, making it complete for an 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?

The tool takes zero parameters, so the schema carries no parameter meaning to supplement; the baseline for no parameters is 4. The description correctly does not invent arguments, instead describing the returned payload.

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 names a specific resource (latest WHOOP status) and enumerates precisely what is returned: recovery score/zone/HRV/RHR/SpO2/skin temp, last night's sleep details, and today's strain with calories and heart rate. It also distinguishes itself from siblings by naming the trend/analysis tools for multi-day questions.

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

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

It explicitly states when to use it first ('how am I today?', 'should I train hard?') and when to use alternatives instead ('For more than one day, use get_recovery_trends, get_sleep_analysis, get_strain_history or get_workouts'). No inference is required.

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 mark it read-only, idempotent, open-world, and non-destructive. The description adds substantial behavior beyond that: it fetches live data on every call, keeps no copy, reports if WHOOP can't be reached, and instructs the caller to use get_auth_url if not connected. It also explains the 'unscored' strain case, which is genuinely useful 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 front-loaded with the core result and output format, then adds usage guidance, behavioral notes, and error handling in a logical order. Every sentence earns its place, and the length is justified by the density of useful 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?

For a single-parameter tool with no output schema, the description is remarkably complete: it details the return shape, sorting, field semantics, live-fetch behavior, failure mode, and authentication prerequisite. An agent has everything needed to call this correctly and interpret the result.

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%, so the schema already documents the `days` parameter well. The description adds practical usage semantics by mapping day values to common questions ('7 for the last week, 30 for the last month') and reiterating the maximum of 90, which enriches the agent's understanding of parameter intent.

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 ('Returns individual workouts from the last `days` days') with precise behavioral details like ordering ('newest first') and output format ('Markdown table'). It also distinguishes itself from the sibling get_strain_history by scoping its purpose to workouts only.

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

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

The description explicitly tells when to use the tool ('questions about specific sessions or training volume'), gives a direct alternative ('for whole-day strain... use get_strain_history'), and provides concrete day-range mapping (7, 30, up to 90). This gives an agent clear selection criteria.

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