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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is clear. Description adds that it returns title, member_count, messages with sender/body/attachments/reply-to/timestamps. But does not disclose pagination behavior (cursor) or error cases. Adds some value but not beyond 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?

Two short paragraphs, front-loaded with the core action. Every sentence is necessary: purpose, ordering, membership requirement, return fields, authentication. No filler.

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?

With output schema presumably detailing return format, the description covers the essential: auth, membership, ordering, key fields. Could mention error cases (e.g., not found, not member) or rate limits, but overall adequate.

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% and already describes both parameters. Description adds ordering info ('newest first') which is not in schema. That adds meaning beyond schema. However, no extra detail on conversation_id format or limit usage beyond what schema says.

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?

Clearly states it fetches messages from a group conversation by ID, newest first. Distinguishes from siblings like colony_list_group_conversations (list vs fetch) and colony_get_conversation (likely direct messages). Verb 'Fetch' plus resource 'messages from a group conversation' is specific.

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?

Says 'caller must be a member' and 'requires authentication', which gives context. However, it does not explicitly tell when to use this vs alternatives (e.g., colony_get_conversation for DMs, colony_search_group_messages for filtering). Implied but not explicit.

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