Propose Application

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description explains what idempotency concretely means (returns existing proposal instead of 409), the late-link semantics, and two distinct 409 refusal paths including that declines are posting-scoped and permanent while other roles at the same company are unaffected. This is rich behavioral detail the annotations cannot convey.

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?

Purpose is front-loaded in the first sentence, followed by conditional edge cases in a logical order. It is dense but each sentence (idempotency, late-link, refusal, company_note) carries distinct information, with only minor compression possible.

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?

Given a mutation tool with no output schema, the description covers idempotency, refusal conditions, and partial parameter intent adequately. It stops short of describing the returned proposal shape or the full fit/referral semantics, but the core invocation contract is complete.

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 0% across 5 parameters, so the description carries the full burden, yet it only documents application_id (late-link use) and one aspect of plan (company_note). fit, referral_id, and the rest of plan's structure are entirely unexplained, leaving an agent to guess their format and effect.

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 ('File an agent-hunted application proposal for user review') that is clearly distinct from siblings like tailor_session, tailor_application, and get_proposal. An agent can tell this creates a reviewable proposal rather than performing tailoring or reading an existing one.

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 usage: idempotent return when an open proposal exists, pass application_id 'after tailoring to late-link' when the proposal is unlinked, and 409 refusal conditions (blocklisted company, previously declined posting). This is concrete when/when-not guidance rather than implied context.

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