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

Adds real value beyond the annotations: the 48h deduplication rule by sha256 and the push-vs-poll delivery choice are behavioral facts not derivable from schema or annotations. Doesn't cover auth, rate limits, or failure modes, so not a 5, but the disclosed dedup and webhook behaviors are the important ones here.

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?

Three sentences, each carrying distinct payload: what it does, how to get results, and the dedup rule. Front-loaded with the core action, no 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 submit-and-poll job tool, the description covers what an agent needs: the operation, both result-retrieval paths, and the idempotency behavior. Combined with the output schema and complete parameter docs, nothing material is missing.

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% and each parameter is fully documented in the schema, including the SSRF re-validation on redirect hops. The description adds only that fetching is server-side ('from file_url server-side'), which is useful framing but not supplemental syntax or constraints. Baseline 3 is correct.

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 ('Submit an APK for static teardown analysis') and enumerates the analysis scope (manifest, permissions, signing, SDK detection, tech stack, locales). Clearly distinguishes itself from siblings like apk_teardown_job_status by describing submission rather than status retrieval.

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 follow-up tool (poll apk_teardown_job_status) and an alternative delivery mechanism (set webhook_url for push). Also tells the agent when submission is a no-op (identical sha256 within 48h returns existing job). This is essentially complete routing guidance.

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