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

Goes far beyond the annotations: it discloses that a sign-in code and link are emailed, that no tool accepts the code, the exact status values (verification_sent, email_required, not_a_cv), that contacts and document numbers are withheld, that drafts expire in 24 hours, and a rate limit of 6 CVs per 10 minutes. These are exactly the side effects and constraints an agent needs for a non-idempotent, open-world mutation.

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?

Dense and front-loaded: the core transformation and the email handoff come first, then return shape, then retry rules, then limits and exclusions. It is a long single paragraph and the return-value enumeration could be tightened, but nearly every sentence carries operational value.

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, and the description fully compensates by enumerating the return payload (status, masked email, handoff_url, up to 5 matched_vacancies, user_message, next_actions) and what is deliberately omitted. Combined with the retry path and expiry, an agent has everything needed to invoke and interpret the 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 coverage is 100%, so the baseline is 3, but the description adds procedural meaning the schema only hints at: the email argument is a fallback used only after email_required, and the retry must resend the same text alongside the email. It also frames the CV content expectations (sea service records, any language) rather than leaving them to the schema alone.

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+resource: turning a seafarer CV into a Krew Guru profile draft, with the domain spelled out (sea service records, ranks, vessels, certificates). It is clearly distinguishable from siblings like get_profile_draft_status and search_maritime_jobs, which handle draft status and job search rather than CV ingestion.

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 names the triggering situations ('seafarer asks to create or update a Krew Guru profile from a CV or to find jobs matching a CV') and three exclusions (other people's CVs without consent, non-maritime CVs, employer/vacancy data). It also prescribes the follow-up path when status is email_required, so the agent knows the retry alternative.

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