add_application

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral detail beyond that: which domains are read in full, that a LinkedIn link is re-tracked on the company's own board, that status 'applied' is only valid once the person has applied, and that pasted text enables scoring. It stops short of auth/rate-limit context, so not a 5.

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 clause, followed by the url-vs-manual branch and then the sibling alternative. Dense but every sentence carries a decision the caller must make; minor tightening of the parenthetical examples is 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?

For a 9-parameter tool with no required fields, an output schema, and full annotation coverage, the description supplies exactly the missing decision context: which input mode to pick, what status values mean, and the mark_job fallback for dedup. Return values and the timing parameters are covered by the output schema and 100%-described input schema.

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 cross-parameter conditional logic the schema does not: company and title 'may be left out' when url is a readable job link, and text substitutes when a link can't be read. It also clarifies the meaning of the default status value ('applied' only after the person applied), which is more than a restatement.

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 (add) and resource (an application/job jobwatch didn't find), and scopes it precisely as jobs the tracker missed (referrals, recruiters, LinkedIn). It also names the sibling it is not — mark_job — for jobs already tracked, so an agent can route correctly without opening schemas.

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?

Explicit when-to-use ('a job jobwatch didn't find'), when-not ('for a job jobwatch already tracks ... use mark_job instead'), and the conditional split between supplying a readable url versus company+title+text. Alternatives and preconditions are named rather than implied.

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