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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds useful behavioral context: it explains the V2 contextual identity requirement and that providers may only guarantee uniqueness inside a chat. This goes beyond the annotations and helps the agent understand why both IDs are needed, without contradicting the safety profile.

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 verbose, repeating the parameter descriptions almost verbatim. It is front-loaded with the core purpose and then covers both ID types, but it could be trimmed significantly without losing value. It is structured in clear paragraphs, but the redundancy with the schema hurts conciseness.

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?

Given the absence of an output schema, the description sufficiently explains how to call the tool correctly: it details how to resolve chat_id and message_id, including the optional account_id handling. It covers the prerequisites and flow, so an agent has what it needs to invoke the tool. The lack of return-format details is acceptable for a read-only retrieval tool.

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% – each parameter has a detailed description. The tool description largely repeats the same information (e.g., chat_id and message_id definitions, how to obtain them). It adds minimal new meaning beyond the schema, so the baseline of 3 applies.

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 'Get one exact message' – a specific verb and resource. It clearly states the tool retrieves a single message, and the requirement for both chat_id and message_id distinguishes it from listing or mutation tools. The purpose is unambiguous and distinct from siblings like messaging_list_messages or message_delete.

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 gives explicit flow guidance: 'If starting from a person/topic, resolve chat first, list messages, then reuse both IDs.' It also specifies what not to pass ('Never pass: person name, user_id, message_id'). However, it does not name alternatives or explicitly state when not to use this tool, though the implied workflow covers that.

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