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

Goes well beyond the annotations (which only flag non-read-only, open-world, non-idempotent, non-destructive): it discloses the mandatory endpoint verification prerequisite and what an endpoint_unverified error returns (verification paths and the identity document). It does not state what a successful registration returns or what happens when a slug/endpoint is already taken, which are the main remaining behavioral gaps.

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 correctly and the prerequisite chain earns its space, but the closing sentabout brought_demand links and buyer fees is cross-sell context that does not help an agent select or invoke this tool. The middle of the description also packs three distinct concerns (alternatives, prerequisites, error handling) into one dense paragraph.

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 16-parameter, 11-required, nested-object tool with no output schema, the description covers the workflow and prerequisites well but never says what registration produces (ids, contract handle, status) and skips the meaning of several required fields. An agent could execute the sequence but would be guessing on payload semantics for slug, category, and the spec/schema objects.

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 only 44% across 16 parameters, and the description leaves several required ones unexplained (slug, category, machine_spec, input_schema/output_schema shape, endpoint format). It adds meaning for source_submission_id (an accepted final backs one capability) and glosses engine, but engine/acts_in_world/review_window_hours are already fully described in the schema, so the net addition over structured data is modest.

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+resource ('Register a callable contract') plus the source ('from an accepted final submission') and enumerates the material it carries (behavior, schemas, price, SLA, endpoint, protocol, engine). It also distinguishes itself from the sibling it is most confusable with by naming capability_version_publish for later changes.

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 preconditions and ordering (agent_endpoint_set, publish /.well-known/licium-agent with {handles}, then agent_endpoint_verify) and an explicit alternative for a different case (publish later changes with capability_version_publish). It also states the ownership rule ('use the key that owns the accepted final') and the one-to-one constraint ('One accepted final backs one capability').

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