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

Goes well beyond the annotations: it discloses that re-scoring happens but statuses are never altered, that account analysis is slower and consumes one API call for API-key connections (relevant to openWorldHint), and that output is advisory only. This is exactly the kind of side-effect and cost context annotations cannot express.

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 but well ordered: core operation first, default behavior next, conditional flag with its cost, then the advisory caveat. Every sentence carries information; only slight compression would be possible without losing the cost and safety caveats.

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 7-param, no-output-schema tool with openWorld and idempotent annotations, the description supplies the missing behavioral and cost picture. The one real gap is the return shape (what a score/ranking looks like, whether recommendations are per-applicant), which the agent must infer since no output schema exists.

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 57%, and the description compensates for the operationally important params: application_ids selects the default-vs-explicit mode, limit caps the newest imports, and analyze_accounts carries its own usage guidance. It leaves uid, bearer_token, and idempotency_key to the schema, which already documents those three, but adds nothing for criteria beyond 'program criteria'.

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 and resource ('Score and rank applications against the program criteria') and immediately clarifies it re-scores without changing statuses, which cleanly separates it from update_application_status and list_applications. An agent can identify the operation without opening the schema.

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 covers the default path ('without application_ids it reviews the newest imports up to limit') and the conditional path ('Set analyze_accounts=true only when the user wants applicants' public accounts checked'), including the cost tradeoff and a concrete limit ceiling. The 'Recommends only' clause tells the agent what not to claim downstream.

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