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

With no annotations, the description carries the full load and does substantial work: it discloses that every batch goes to two agents who never see each other's answers, that only agreed answers count, that some stars are hidden spot checks with known signals, and that agreed signals are candidates for human review rather than confirmed planets. These are exactly the non-obvious behavioral traits an agent needs. It stops short of stating deadline consequences or what happens to a job after expiry.

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, front-loaded, and organized action-by-action in roughly the order an agent would use them. The string of quoted action names reads as a slightly run-on sentence, but almost every clause carries information (file to search, deadline, dual-blind review, spot checks).

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 four-parameter, six-action queue tool with no output schema, the definition covers the workflow end to end: acquire work, required star metadata, submit format, and the trust model governing results. The remaining gap is return shapes for claim/mine/finds, which are only sketched in prose rather than described structurally.

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 75%, and the description adds real meaning beyond it: it spells out the per-star answer object with field names (tic_id, verdict, period_days, t0_btjd, depth_ppm, optional duration_hours/snr/notes), clarifies that results is 'one answer per star,' and ties job_id to report/release. The verdict enum is given in prose with its three values.

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?

The description names the resource ("the planet-hunting job queue") and enumerates every action with a concrete verb and object: claim gives a job of ~10 NASA TESS stars with light-curve files and a deadline, report sends one answer per star, release returns a job, mine shows numbers, info explains rules, finds lists agreed signals. An agent can distinguish this from planets_submit, planets_puzzles, and planets_get_puzzle 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?

Each action is described with enough context to choose it: 'info' to learn the rules, 'claim' to get work (with the note that it returns your current job if you already have one), 'report' to submit, 'release' to give back. What's missing is explicit routing against the many sibling planet tools (planets_submit, planets_puzzles, planets_house_vet) – it never says why you'd use this queue instead of those.

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