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

Annotations only declare readOnlyHint=false/destructiveHint=false, so the description carries the real burden and does: it discloses server-side verification of proof of possession, the publication side effect at /.well-known/tango-worker-keys/{worker_id}.json, and a hard failure mode ('requests containing a private key are rejected').

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?

Front-loaded with step ordinal and the key constraint; every sentence adds something (constraint, verification behavior, publication, negative case, alternative mode, reference link). Slightly dense, but 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?

With no output schema, the description still explains the observable outcome (key published at a well-known URL after verification) plus prerequisites and a rejection case, leaving nothing an agent needs in order to call this correctly.

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 already documents signed_nonce format and the JWK shape; the description reinforces the critical semantic constraint ('Never send a private key', 'ONLY ... public JWK', signature 'over the nonce from request_key_challenge') and disambiguates which challenge the signature must bind to.

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+resource ('Submit ONLY your Ed25519 PUBLIC JWK') and situates it precisely in a workflow ('Step 2 of attested mode'), which cleanly separates it from siblings like request_key_challenge (step 1), issue_worker_key, and rotate_worker_key.

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 an explicit precondition ('Step 2', nonce from request_key_challenge) and a when-not with a named alternative: 'Only register an attested key if you can persist the private key across sessions; otherwise use delegated mode, where Tango signs on your behalf.' That is exactly the routing guidance an agent needs.

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