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

Annotations only say it's a non-idempotent, non-destructive write; the description goes far beyond by disclosing that it files a real application under a real person's name, commits them to a binding program, requires no auth, that a token only attributes, and that a second submission is rejected. It names the exact fields the agent must not fabricate and explains the claim_token is shown exactly once.

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?

The paragraph is front-loaded with the action and then layers warnings, prerequisites, constraints, and return shape in a logical order with no filler. It is dense and slightly run-on, but every sentence carries new operational information.

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?

There is no output schema, but the description still enumerates the return object ({ ok, application_id, claim_token, status, failed_gates, cohort, message }) and covers auth, idempotency behavior and the critical claim_token handling. Nothing an agent needs to invoke this 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?

With 100% schema coverage the baseline is 3, but the description adds meaning beyond the schema by flagging that nda_ack, commit_5_weeks and in_person_sf answers are 'promises they have to keep' that must be confirmed, and by specifying that all answers need the human's confirmation. This elevates how to treat the required fields, though it doesn't restate enum values the schema already lists.

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 application) and resource (the 20-person spatial-computing beta) with scope details (5-week, in-person, NDA-bound). It routes the agent to ic_spatial_beta_program for the catalog and implicitly separates itself from the status/read siblings. An agent can tell what this does 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?

Gives explicit prerequisites ('Call ic_spatial_beta_program first for the catalog and the exact allowed values') and a hard behavioral rule ('CONFIRM EVERY ANSWER WITH YOUR HUMAN FIRST and never invent one on their behalf'). It also states the one-application-per-email constraint and that duplicates are refused rather than merged.

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