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

Even though annotations show readOnlyHint=false, the description goes much further: it names the files written (persist.path, ~/.conduit/active), the credential fields, the chmod 0600 permission, and the auto-generation/omit behavior for handle and avatar. It also warns against inventing optional human-facing values, which is crucial non-obvious behavior. No contradictions with annotations.

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 description is long, but the BEFORE/AFTER structure and explicit optional-field rules make it scannable. Every sentence carries task-critical instructions for a complex 10-parameter creation tool, and little is filler. It is appropriately dense rather than bloated.

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 tool with 10 parameters, side-effecting filesystem writes, and required follow-up calls, the description covers prerequisites, postconditions, sequencing, and hallucination guardrails. Combined with the output schema and parameter schemas, an agent has enough to invoke and choreograph this tool 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?

With 100% schema description coverage, the baseline is 3; the description adds real usage semantics beyond the schema, such as 'only if the human stated them — never invent', omiting avatar to get a random invader+gradient, and including postcode in default_destination before supply_search. It does not add detail for preferences or business_profile, but the schema already documents those.

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 opens with 'Register an agent' and specifies the core input (ES256 P-256 public JWK JSON string plus optional payment rails and destination). This is a concrete verb+resource statement. The subsequent 'do NOT register again' and reference to agent_update make it clear this is the creation/registration sibling, not an update or lookup.

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?

It gives explicit BEFORE guidance: inspect ~/.conduit identity files and reuse an existing agent_id rather than registering again, unless the human explicitly requests a new agent. It also choreographs the follow-up actions (agent_update with default_destination+postcode before supply_search), so an agent knows when this tool is the right call and what to do next.

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