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

Annotations declare non-read-only and non-idempotent, but the description adds essential behavior: writes are exact and deterministic, prerequisites exist (competencies), a hard limit of 50 skills applies, and stale source_stage versions trigger a 409. No contradiction with annotations; it supplements them with concrete constraint and failure details.

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 entire description fits in three short sentences, with the core purpose front-loaded and constraints packed efficiently. Every clause adds information without repetition or 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 mutation tool with nested objects and no output schema, the description covers key constraints and conflict behavior, but omits item field semantics and failure modes (e.g., what happens if competencies are absent or the 50-skill limit is exceeded). It is adequate for a simple call but leaves ambiguity for complex inputs.

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 0%, so the description must clarify parameter meaning. It explains source_stage's shape and staleness behavior, and conveys that items are written verbatim. However, it does not describe the individual item fields (id, name, skill, title, details, category, description, requirement) that appear in the schema, leaving their semantics and required combinations ambiguous.

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 'Add job skills to a draft' and then qualifies it with 'exactly as written — deterministic, no AI generation', making the tool's purpose unmistakable and separating it from sibling generate_skills. It also distinguishes from update, delete, and clear tools on the same draft resource.

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 supplies usage preconditions: 'Requires competencies' and 'the resulting stage must stay within 50 skills'. It also describes the optional source_stage parameter and warns about a 409 on stale versions. It implies the alternative of generate_skills through the 'no AI generation' clause, but does not explicitly name sibling tools or state when not to use this tool.

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