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

Annotations cover the safety profile (readOnlyHint=true), so the description's job is to add operational context — and it does: the 1-credit cost, language-agnostic input, and the shape of the emitted criteria (weight 1-3, mandatory flag, rationale). That is meaningful disclosure beyond the annotations, though nothing is said about limits on size or failure modes.

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 with zero filler; the transformation and output shape are front-loaded before the downstream hint and cost note.

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?

No output schema exists, so the description compensates by naming the returned fields and their value ranges, plus the credit cost and the follow-up tool. An agent has everything needed to call it 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?

Only one parameter and schema coverage is 100%, so the schema already documents job_text fully. The description adds 'any language' as a semantic constraint on the input, which is a small but real addition — baseline 3 is appropriate here.

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 (extract) and resource (job criteria) with the transformation spelled out: job description text in, weighted matching_criteria[] out. It names the downstream consumer (match_candidate), so an agent can place it in the pipeline without opening the 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?

States the downstream step explicitly ('Feed the result to match_candidate') and discloses the credit cost, which is real usage guidance. It stops short of saying when NOT to use it or how it differs from siblings like parse_resume, but the intended pipeline position 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?

Annotations only declare readOnlyHint and openWorldHint, so the description must add the operationally important facts, and it does: the cost ('Costs 1 HireLayer credit') and the return shape. Missing any note on rate limits or failure modes, so not a 5.

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-loaded with what the tool does and what it returns, followed by the sourcing/prerequisite and the credit cost. 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?

With no output schema, the description compensates by describing the return value (a 0-1 score plus per-criterion evaluation), and it discloses the credit cost and upstream dependencies. Nothing essential for correct invocation is omitted.

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 baseline is 3. The description adds value beyond the schema by naming where matching_criteria originates (extract_job_criteria) and where candidate_text comes from (info_resume.text), which the schema does not state.

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 ('Score one candidate against a job') and quantifies the output ('score between 0 and 1 and an evaluation of each criterion'). The singular 'one candidate' implicitly contrasts with the sibling rank_candidates, so the agent can distinguish 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?

Explicitly routes the agent to siblings: criteria come from extract_job_criteria and resume text from parse_resume (info_resume.text), which is real pipeline guidance. It lacks an explicit 'do not use for multiple candidates, use rank_candidates' exclusion, 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 only declare readOnlyHint and openWorldHint; the description goes further by disclosing the credit cost, the file size limit, and the accepted formats. It still does not cover authentication requirements, failure behavior, or what happens to the uploaded file by default, which keeps it short of a 5.

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?

A single dense sentence with the purpose and output shape front-loaded, followed by the input modes and cost. The long format list is necessary information, not padding.

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 return-value burden and does so by naming the structured fields and info_resume.text. Formats, size, cost and input modes are covered; error behavior and default storage semantics are the only notable omissions.

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 all four parameters are already documented. The description reinforces the file_path-vs-file_url choice and names one output field, but adds no format or syntax detail for application_id or do_not_store_data 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?

States a specific verb (parse) and resource (resume) and enumerates the exact output: contact details, work experience, education, languages, skills, and full text in info_resume.text. No sibling tool overlaps with resume parsing, so the agent can distinguish it immediately.

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?

Gives clear operating context: accepts either a local file_path or a public file_url, lists supported formats, and states the 4.5 MB ceiling and 1-credit cost. It does not name exclusions or alternative tools, but the usage conditions are explicit enough to act on.

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 openWorldHint=true, and the description is consistent with them. It adds a genuinely useful behavioral fact beyond the annotations: a billing cost of 1 HireLayer credit per call, which affects how freely an agent should invoke it. It stops short of describing the ranking output or failure modes.

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, zero filler, with the core operation and its cardinality limit front-loaded and the cost caveat second. Every clause 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?

No output schema exists, so the description carries the burden of explaining what comes back, and it says nothing about return shape (ordering, scores, per-candidate errors) or behavior when a candidate is malformed. The credit cost and batch limit are covered, but the return-value gap leaves the agent guessing.

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 50% and the schema's own descriptions are terse ('Job description.', 'Resume as plain text.'). The description clarifies that job_text is one shared job description and candidate_text is resume text, but adds no syntax, format, or ID-uniqueness detail 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?

States a specific verb (rank) and resource (candidates) plus the batch scope ('up to 10 candidates against the same job description, from their resume texts'). This implicitly separates it from the single-pair match_candidate, but no sibling is named, so the differentiation is inferred rather than explicit.

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 'up to 10' batch framing implies when this is preferable to match_candidate, and the credit cost hints at deliberate use, but there is no explicit when-to-use or when-not-to-use guidance relative to parse_resume, extract_job_criteria, or match_candidate.

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 openWorldHint=true, so the safety profile is covered. The description adds a genuinely non-obvious behavioral trait beyond structured data: 'Costs 1 HireLayer credit,' which lets an agent reason about the price of calling this (and potentially batching). It still says nothing about behavior for unmatched or ambiguous skills.

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, front-loaded with what the tool does, followed by the cost. Every clause earns its place; no filler or restatement of the name/title.

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?

No output schema exists, so the description carries more of the return-value burden; it states IDs are returned but not the shape of the response (list, confidence, unmatched entries). With only two simple parameters and annotations covering safety, it is close to adequate, but the resolution result semantics remain underspecified for a paid taxonomy-mapping call.

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 schema already documents 'text' and the fr/en 'language' enum. The description adds the useful nuance that 'text' accepts anything from a single skill to a full section, but it does not clarify that the 'language' parameter controls the language of the returned labels rather than the input language, and it says nothing about output format beyond 'with their IDs.'

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 (map/resolve) and resource (free-text skills) plus scope (French or English, single skill, compound string, or whole section) and the concrete output (HireLayer taxonomy skills with their IDs). This is clearly distinguishable from siblings like parse_resume and match_candidate, which do extraction and matching rather than taxonomy resolution.

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 input scope ('one skill, a compound string or a whole skills section') implies when the tool is applicable, but there is no explicit when-to-use guidance and no mention of alternatives or when-not to use it. An agent could reasonably wonder whether parse_resume or extract_job_criteria is the better first step, and the description does not resolve that.

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