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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds useful non-annotation context: that the call is free and that polling continues until a 'done' flag flips true. It stops short of describing failure states, terminal-error conditions, or backoff guidance.

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 terse sentences, no filler: cost, identity/provenance, and the polling condition are each front-loaded and independently actionable.

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 values needn't be spelled out, and the tool is a simple single-parameter poller whose core loop is described. It is nearly complete, with only failure/terminal-error handling left implicit.

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?

Only one parameter (jobId) with 0% schema description coverage, so the description must carry the load. It does imply provenance ('a job created by blackwood_pdf_extract'), which tells the agent where jobId comes from, but adds no format or validity details beyond length constraints already in the schema.

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 (status/result of a PDF extraction job) and names the sibling tool that creates the job, so an agent can distinguish it from blackwood_pdf_extract and the other *_status tools at a glance.

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 clear operational guidance — 'Poll until done is true' — which tells the agent both when to call it (after blackwood_pdf_extract) and how to terminate polling. It doesn't explicitly contrast with the other *_status siblings, but the workflow context is unambiguous.

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