agent_register

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

With no annotations provided, the description carries the full burden and does meaningful work: it discloses the authorization model (self-only, PERMISSION_DENIED on violation) and the fail-closed capability policy against the central catalog. It omits whether unspecified fields are preserved or cleared, and whether updates are idempotent.

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?

Compact and front-loaded: the action, the self-only restriction, and the capability constraint each appear in their own short clause, with the doc link last. No filler, though the clipped style borders on telegraphic.

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 need not be explained. However, the description leaves two real gaps for a mutation tool: whether this creates an agent that doesn't yet exist (the name implies registration) and why a required agent_id is needed if the operation is strictly self-only. For a write tool with no annotations, these should be resolved.

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% and the schema already explains role matching, the global agent_id, free-form metadata, and the three capability input shapes with the fail-closed rule. The description restates the field list and the catalog constraint without adding syntax or format detail beyond the schema, so the baseline 3 applies.

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: update the caller's own agent profile, with the affected fields (role/capabilities/metadata) enumerated. It is clearly distinguishable from read-oriented siblings like agent_get, agent_list, and agent_whoami. The tool name 'agent_register' suggests creation rather than update, which slightly muddies the read of the purpose, but the prose is unambiguous about the action.

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 (SELF-ONLY, otherwise PERMISSION_DENIED) and routes capability discovery to capability_list. It does not, however, state when an agent should call this versus agent_whoami (read) or when a first-time registration versus a subsequent edit applies.

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