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

Annotations only signal readOnly=false, idempotent=false, and openWorld=true. The description adds meaningful behavioral context: 'One free draft, then it needs a Calibrd pass; the tool says so and gives the link.' It also explains language behavior based on the posting. 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 compact and front-loaded: purpose first, then the usage restriction and the paywall behavior. Every sentence earns its place with no redundant 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 content-generation tool with a fully documented schema, the description covers the essential trigger, output language, and the free-draft/pass constraint. There is no output schema, but 'drafts a cover letter' sufficiently implies the return. Minor edge cases like non-en/fr postings are not addressed, but they are not critical.

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

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

Schema description coverage is 100%, so parameters are already well documented. The description's mention of 'from the person's CV' reinforces cv_text but adds little beyond the schema. 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 states a specific action: 'Drafts a cover letter for one job from the person's CV, in the posting's language.' This clearly identifies the resource, input, and output, and it is easily distinguished from siblings like calibrd_score_job and calibrd_review_cv.

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 an explicit trigger: 'Call it only when the person asks for a cover letter.' It does not enumerate alternatives or detailed exclusions, but the condition is specific enough to guide selection.

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 signal readOnly and non-destructive behavior. The description adds useful operational context beyond that: the tool generates a checkout link rather than charging directly, externalizes payment to Stripe, and affects the daily report cap. No contradiction with the annotations exists.

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: the first defines the action and effect, the second clarifies payment mechanics, and the third gives precise call triggers. The description is front-loaded and contains no 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 two-parameter tool with no output schema, the description is complete: it explains what is created, what the pass does, how payment works, where pricing lives, and when the tool should be called. 'Checkout link' sufficiently implies the return value 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?

Schema description coverage is 100%, so the baseline is 3. The description mentions the tier values (week, month, search) but does not add meaningful detail beyond the schema, which already explains durations and the currency default. The description therefore contributes little extra parameter semantics.

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 and resource: 'Creates a checkout link for a Calibrd pass', and clarifies the pass benefit ('removes the daily report cap and unlocks every tool'). The tier list (week, month, search) further distinguishes it from the sibling tools, which are about status, reports, scoring, and document review.

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

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

Explicitly states when to invoke: 'Call it only when the person asks to buy, or after a tool said it needs a pass.' It also provides an exclusion by clarifying that payment happens on calibrd.com through Stripe, 'never in the chat', so the agent knows not to use it as a payment-processing 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?

Annotations already cover idempotency, read-only vs mutating, and open-world behavior. The description adds useful non-obvious context: 'Free, three a day; a pass removes the cap' and that providing a CV additionally scores it against the job. No annotation contradiction exists.

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 with no filler: the first states the core function and outputs, the second conveys the CV-dependent behavior, quota, and usage trigger. Information is front-loaded and every sentence earns its place.

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

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

For a tool with no output schema and six parameters, the description captures purpose, output contents, optional CV behavior, quota, and the main use case. It is complete enough for an agent to invoke it correctly, though explicit routing to sibling tools would be stronger.

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

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

Schema description coverage is 100%, so the schema already documents all six parameters in detail. The description adds only a mild semantic hint that a CV enables CV-vs-job scoring, which does not meaningfully go beyond what the schema already states.

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

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

The description uses a specific verb ('Builds') and resource ('the full Calibrd report for one job posting'), and lists concrete deliverables: shortlist read, gaps, questions, interview process, and compensation benchmark. The 'full report' framing clearly differentiates it from narrower sibling tools like calibrd_score_job, calibrd_review_cv, and calibrd_cover_letter.

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 an explicit trigger: 'Call it when someone wants to prepare for a specific role.' It does not name alternatives or state when not to use this tool, so it falls short of the strongest routing guidance, but the context is clear.

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

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

The description discloses useful operational behavior beyond the annotations: it produces two-way scoring and rewrite suggestions, and it is free. The annotations already cover idempotence and non-destructiveness, and the description adds no false safety claims, so no contradiction exists.

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 short sentences front-load the core behavior, then the tailoring instruction, then the trigger condition. There is no filler or redundancy; 'Free' is the only peripheral detail and is short enough not to hurt.

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

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

With no output schema, the description adequately signals return content: scores from two perspectives plus fix and rewrite suggestions. It also gives the key usage condition (job posting tailoring). It does not enumerate output format details, but the operation's output is described well enough for an agent to select and invoke 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 input schema already documents every parameter, including the at-least-200-character rule for job_description and the job_url preference, so the description has little to add. 'Pass the job posting' generically maps to job_description/job_url but adds no parameter-level semantics beyond the schema. Baseline 3 is appropriate given 100% schema description 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 first sentence names the exact action (scores a CV) and differentiates the output from a plain score by describing two distinct review modes: recruiter reading and ATS parsing, plus a list of fixes and rewrites. The trigger phrase 'someone asks how their CV reads or what to change' anchors the domain and separates it from sibling tools like calibrd_cover_letter or calibrd_report.

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?

'Call it when someone asks how their CV reads or what to change' is an explicit trigger condition, and 'Pass the job posting to tailor the review' explains the recommended input context. It does not explicitly name alternatives or when-not-to-use cases, so it stops short of a 5.

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

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

Annotations already cover idempotent and non-destructive behavior; the description adds useful context beyond them: 'Free, no daily cap' addresses rate limits, and the explanation that it both scores the match and evaluates the CV as a recruiter/ATS clarifies what a call actually produces. It does not contradict the readOnly=false annotation (external fetching is implied but harmless).

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 information-dense and front-loaded with the core behavior before usage guidance and the sibling alternative. It is slightly long and the third clause ('as a recruiter and as an applicant tracking system read it') is grammatically awkward, but every sentence contributes actionable 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?

With no output schema, the description adequately previews the return content: a 0-100 match score, gaps at that level, and customized CV scoring from two perspectives. It also contextualizes external fetching via the job_url parameter in the schema, so an agent knows why openWorld=true is set. It does not detail response structure, but that is not necessary for correct invocation.

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

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

Schema description coverage is 100%, so the schema already documents all six parameters clearly, including the choice between job_url and job_description. The tool description itself adds little parameter-level meaning; it only reinforces the match/gap intent of the tool, which is the baseline expected when the schema carries the detail.

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

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

The description opens with a specific verb and resource: 'Scores how well a person's CV matches one job posting (0 to 100)', and adds what output to expect: gaps, recruiter perspective, ATS perspective. It also names the sibling tool it is not ('use calibrd_report for the full read'), so an agent can distinguish it from calibrd_report and the other siblings without opening 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?

It explicitly states when to call: 'Call it when someone asks whether to apply, or to triage several postings'. It also gives an alternative and a follow-up condition: 'use calibrd_report for the full read on the ones that score well'. This is clear routing guidance beyond what annotations or schema provide.

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, so the safety profile is covered. The description adds useful context by enumerating what the status includes (days left, reports left, mock rounds, included features), giving the agent a concrete idea of the tool's informational behavior 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?

Two tight sentences: the first fronts the resource and data content, the second gives when-to-call guidance, including a sample user query and a prerequisite action. Every clause earns its place and nothing extraneous is included.

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, read-only status tool without an output schema, the description is complete. It names the fields an agent can expect, gives multiple natural-language triggers, and supplies an ordering constraint ('before suggesting a pass'), so an agent can select and invoke it correctly without additional context.

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

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

The tool has zero parameters and schema description coverage is 100%, so the schema carries the full parameter story. The description appropriately treats the tool as a no-argument status lookup, which is consistent with the empty parameter list. Nothing more 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 clearly identifies a specific resource (the person's Calibrd account) and defines the kind of information returned: free/pass status, days left, reports left today, mock interview rounds left, and included features. This distinguishes it from sibling tools like calibrd_get_pass, which would handle obtaining a pass rather than reporting account status.

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 triggers: any question about the Calibrd account, plan, pass, reports, mock rounds, or 'what do I have on Calibrd', plus the instruction to call it before suggesting a pass. It does not explicitly name alternative tools or when not to use it, but the usage context is very clear.

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