Record a gap

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

Annotations only declare idempotentHint=false and destructiveHint=false; the description adds the meaningful part by explaining the upsert semantics -- count increments and source is appended if the term exists, otherwise it is created with count 1 -- and that duplicates are never produced. It does not cover permissions, the response shape, or how the added source affects the existing entry, but the mutation consequences are well disclosed and consistent with the non-idempotent hint.

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 purpose and mutation behavior are front-loaded in the first three sentences, with usage rules following. Five sentences is on the long side for a three-parameter tool, and 'It never duplicates' partially overlaps with the later 'Never call it for something already in skills.md', but every sentence still carries 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?

For a mutation tool with no output schema and only partial annotation coverage (idempotency/destructiveness), the description supplies the core context an agent needs: the missing-skill scope, the create-vs-increment behavior, and the exclusion for skills already in the profile. Remaining gaps -- return value and any auth/permission requirement -- are minor for this operation.

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 term, source, and category are all already documented with examples in the schema. The description only implicitly reinforces what 'source' does (it is added to an existing entry), adding no format, naming, or placement detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 precise verb+resource+condition: it records that a job offer asks for a skill the user does NOT have. It also discloses the underlying data behavior (radar entry incremented vs. created with count 1), which distinguishes it clearly from siblings like list_gaps or confirm_skill.

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 explicit when-to-use ('call it once per skill the offer asks for that is missing from the user's profile, including terms the user could not define in an interview') and an explicit when-not ('Never call it for something already in skills.md'). However, it never names the alternative sibling tools an agent should route to for already-known skills (e.g. confirm_skill or update_skill_level), so the exclusion lacks a destination.

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