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

Annotations only provide the generic write-ish profile (readOnly=false, idempotent=false, destructive=false). The description adds substantial context beyond that: the token is placed inside the prompt envelope first, what that token can and cannot call, the prompt_envelope refusal, anonymous-caller behavior (envelope:null), and named error codes (not_found, withheld, revoked, lint_failed).

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?

Information-dense and front-loaded: purpose, then routing, then envelope/token rules, then return shape. Nearly every sentence carries load, though the trailing 'Example: call federation_prompt_run with arguments {}.' adds little and the middle clauses are tightly packed enough to risk skimming.

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?

There is no output schema, and the description compensates by spelling out the exact return shapes ({ ok, body, manifest, envelope {...} } and the failure form { ok:false, code, message }) plus the failure codes. For a stateful, envelope-granting tool this is complete enough to call 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 100%, so both params are already documented, giving a baseline of 3. The description earns above baseline by explaining what ttl_minutes actually controls — that until expires_at the token may call only the tools the prompt names, otherwise error prompt_envelope — which is behavioral meaning the schema's 'How long the run lasts' does not convey.

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 — 'Run a ComOS library prompt (CO 614)' — and immediately contrasts the behavior with the alternative of pasting prompt text. It also names the sibling introspection_prompt_library as the way to find ids, so the agent can distinguish this from discovery tools without opening a 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?

Explicitly says 'Call this INSTEAD of pasting prompt text' and routes id lookup to introspection_prompt_library. It also sets the hard constraint that no tool ends a run early and a second prompt cannot be started on the same token until the first expires, which tells the agent when this call will be refused.

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