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

Annotations only declare a non-read-only, non-destructive write; the description goes well beyond that by disclosing how agent_id is derived ({subject}-{function}), that a permanent_address is minted and "never changes", that the server appends a -v1 generation and preserves the id across rotations, and that auto-created entries are completed rather than duplicated. These are exactly the side effects an agent needs before calling a mutation tool.

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 purpose and lifecycle position, and nearly every clause carries new information (identity derivation, id format, addressing, dedupe). It is dense rather than padded, though the run-on parentheticals ("(capabilities, description)", "(reach: {webhook, note}; your default subscription is filled in)") make it slower to scan than it needs to be.

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 an 8-parameter write tool with an output schema (so return values need no explanation), the description covers identity derivation, dedupe semantics, addressing, and idempotency (via schema). The only material omission is the `role` parameter, which is neither described here nor in the schema.

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 schema description coverage at only 13% (only idempotency_key documented), the description carries most of the burden and does so well: it enumerates introduction fields (name, function, maker, model, runs_on, note) with an example, gives the agent_id regex and format, and explains reach as {webhook, note} plus capabilities/description. It falls short on `role`, which is never mentioned, and display_name is only implied by "the platform derives ... a display name".

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?

Opens with a specific verb and resource: "Register this token's agent in the directory", and immediately anchors it as "onboarding step 4". It also names the discovery sibling (list_agents) and the addressing scheme (agent:<agent_id>), so an agent can place the tool in the lifecycle 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 a clear triggering condition ("First handshake: a token minted without a name") and an explicit alternative path ("Or pass agent_id yourself"). It also warns that a platform-filled entry (source=auto) is "completed, not duplicated", which prevents redundant calls. The one gap: it never distinguishes this from the sibling update_agent, so an already-registered agent has no stated guidance on re-registering vs updating.

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