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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds genuinely non-obvious behavior beyond them: the payload is delivered inline as base64 over the tool channel, there is a hard 4 MB cap, and the network/egress failure mode that motivates the tool. Those are exactly the traits structured fields 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?

Three dense sentences, front-loaded with what the tool returns before the rationale and the fallback. No filler, no repetition of the title or of annotation content.

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?

An output schema exists, so return-value documentation is unnecessary; the description still covers the caller-relevant behavior (inline base64, 4 MB ceiling, sandbox context, fallback path). Nothing an agent needs to invoke it correctly 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 description coverage is 100% for the single required job_id, so the schema already documents the parameter. The description adds the meaningful constraint that the job must already be complete, but gives no further syntax or format detail beyond the schema, so the baseline 3 is appropriate.

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 ('return the finished output of a completed job INLINE as base64') and immediately contrasts it with the sibling get_download_url, which is the file-fetching alternative. An agent can distinguish it from get_download_url and get_job_status without opening any 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?

Gives explicit when-to-use (sandboxed agent environments like claude.ai, Claude Desktop, Cursor where fetching a get_download_url link is blocked), a precondition (call after get_job_status returns 'complete'), and an explicit when-not-to-use plus alternative (>4 MB outputs should use get_download_url). This is a full routing decision in one paragraph.

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