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

The read-only, idempotent, and non-destructive traits are already covered by annotations. The description adds valuable extra context: the stored text should be treated as advisory content only and is not authorization for unrelated writes or external actions. That is a meaningful behavioral guardrail beyond what the annotations state, though it does not cover edge-case behaviors like not-found handling.

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 compact and well-structured: the first sentence carries the full retrieval purpose and contents, and the second sentence adds an important safety caveat. Every clause adds signal and there is no repetition of what the annotations already say.

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?

Even without an output schema, the description enumerates the key components of the returned deliberation, which is enough for an agent to understand what to expect. It omits behavior when neither id nor canonical_key is found, but for a simple read-only lookup tool this is a minor gap rather than a blocking omission.

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 0%, so the description carries the burden. It does add a useful qualifier: canonical_key is 'stable', and it states retrieval is possible by either UUID or canonical_key. However, it does not clarify precedence, mutual exclusivity beyond the schema, or when each key type is more appropriate, so the action compensates only partially.

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 a specific verb, 'Retrieve', and names the resource: a 'shared AI deliberation'. It goes further by enumerating exactly what is returned — question, constraints, attributed contributions, unresolved points, and any user-approved resolution — and identifies the lookup keys (UUID or canonical_key). This clearly distinguishes it from siblings like create_deliberation and list_open_deliberations.

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?

The description makes the intended usage clear: retrieve an existing deliberation using either its UUID or a stable canonical_key. It does not fully spell out when not to use this tool or explicitly name alternative tools, but the retrieval context is unambiguous and the identifier-based lookup is a good implicit usage signal.

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