Review a headline

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

The readOnlyHint=true annotation already establishes this is a non-mutating evaluation, so the description carries a lighter burden. It usefully discloses the rubric dimensions that will be scored (first-60-character role placement, length, vague labels, segments, 'open to' line, target keywords), which is real behavioral context beyond the annotation. It still omits the scoring scale, whether findings are pass/fail or graded, and any thresholds, so it is useful but not rich.

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?

One sentence, front-loaded with the verb and resource, then a compact enumeration of the checked dimensions — no filler or hedging. It is slightly list-heavy and would read better with light grouping, but nothing is wasted.

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 three simple parameters and no nested objects, the tool is low complexity, and the enumerated rubric dimensions partly imply what the response contains. But there is no output schema, and the description never states what 'score' returns — numeric values per dimension, prose findings, or a single grade — nor how missing optional parameters like keywords affect the review. That is the outstanding gap.

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 67%: keywords ("Must-have terms from job postings") and target_role ("e.g. 'AI Engineer'") are already documented in the schema, while headline is undocumented. The description adds some meaning by tying the review to 'target keywords' and to whether the role appears in the first 60 characters, which hints at how target_role is consumed. With the schema doing most of the work, this lands at the 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 pairs a specific verb ("Score") with a specific resource ("a headline") and enumerates the dimensions being evaluated: role in first 60 characters, length, vague labels, segments, 'open to' line, keywords. That is clear and distinguishable from siblings at the object level. It does not, however, name or contrast itself with review_experience, review_profile, or lint_field, so it stops short of the sibling differentiation a 5 requires.

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?

There is no explicit when-to-use, when-not-to-use, or alternative routing guidance. The agent must infer from the name that this applies to headlines versus the sibling reviewers for experience sections or full profiles, and nothing tells it whether this should be run before or after keyword_coverage or lint_field. Usage is only implied by the object of the verb.

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