WerkCV – Dutch CV check

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context beyond the structured fields: 'Free, no AI, nothing is stored' tells the agent there is no cost and that input is not retained, which matters for pasting personal CV text.

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 zero filler; the core purpose is front-loaded and the usage cue follows. Nothing is repeated from the title or schema.

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 carries the burden of describing returns, and it does name the two outputs (a 1-10 grade and a prioritized fix list). It stops short of describing how the grade is structured or what a 'fix' entry contains, so it is strong but not exhaustive.

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 cv_text and locale are already fully documented, including the locale auto-detection and the 200-25,000 character bounds. The description adds no parameter-level information at all, 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 names a specific verb (grades), the resource (a CV), the scale (1 to 10), and the criteria (Dutch hiring conventions and ATS readability), plus a concrete deliverable (the fixes to make first). This is unmistakably distinct from match_vacancy and open_in_editor without opening any schema.

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 gives a clear triggering condition: 'Use when the user wants to know how strong their CV is.' No exclusions or named alternatives are offered, but the context of use is unambiguous.

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, but the description adds context annotations cannot express: it is AI-backed and therefore rate-limited, and nothing is stored. Those are real operational constraints for an agent planning calls. It stops short of stating whether repeated calls can return different results, which matters given idempotentHint=false.

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 tight sentences: what it does, how the output is shaped, then the operational caveats. The most decision-relevant information is front-loaded and no sentence is 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?

There is no output schema, so the description carries the burden of describing the return shape, and it does: a requirement-by-requirement comparison with quotes from both texts and a prioritized list of fixes. Combined with the rate-limit and no-storage notes, an agent has everything needed to call and interpret this tool.

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

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

Schema description coverage is 100%, and the schema already documents character limits, required inputs, locale enum, and a PII-stripping instruction for cv_text. The description only refers generically to 'a CV' and 'one vacancy', adding no format or constraint detail 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?

States a specific verb and resources ('Compares a CV with one vacancy') and even describes the granularity of the comparison, so the agent knows exactly what operation it gets. It does not explicitly distinguish itself from the sibling check_cv, which appears to handle a CV alone; the singular 'one vacancy' hints at the difference but the description never names the alternative.

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 is implied by the purpose: use this when you have both a CV and a vacancy to match. There is no explicit when-to-use, when-not-to-use, or named alternative (check_cv), so an agent choosing between the two siblings must infer the boundary from the tool names alone.

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?

Goes well beyond the annotations by disclosing the lifecycle of the stored data ('stored for at most 60 minutes and deleted the first time the link is opened') and that no account/auth is needed. These are exactly the non-obvious traits an agent needs when handling user CV text, and the write semantics (readOnlyHint=false) are made concrete.

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 with zero filler; the return value leads, the data-retention caveat follows, and the call condition closes. Nothing could be removed without losing 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?

Although there is no output schema, the description explains the return value (a link) and its expiration behavior. Combined with annotations covering safety and a fully documented schema, an agent has everything needed to 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?

Schema description coverage is 100%: locale, cv_text (length bounds, PII removal), and vacancy_text are all fully documented in the schema. The description adds no parameter-level detail beyond that, which is the expected baseline when the schema does the work.

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?

Specific verb+resource: 'Returns a link that opens this CV in the WerkCV editor' states exactly what the tool produces and what it does with it. It is trivially distinguishable from check_cv and match_vacancy, which analyze rather than hand off an editing link.

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 only when the user wants to edit or download the CV' gives an explicit positive trigger with an exclusivity qualifier, implying the tool should not be called for checks or matching. It stops short of naming a sibling as the alternative, so it is clear context without explicit routing.

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