messages_recent

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

With no annotations, the description carries the full behavioral burden. It usefully discloses one return-value trait (own messages carry a To: line naming the recipient), but says nothing about read-only status, permissions, result ordering, or how the defaults behave – gaps that matter for an unannotated, no-output-schema tool.

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?

Three tight sentences with the purpose front-loaded, followed by usage triggers and one behavioral note. No repetition of the schema and nothing extraneous.

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 zero-required-parameter, no-output-schema tool, the description covers purpose, trigger phrases, and a hint at the returned content. It leaves the read-only/nature-of-results characterization thin, but nothing essential to correct invocation is missing.

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 100%, so limit and days_back are already fully documented with their defaults. The description adds no parameter-level meaning, so the baseline 3 for schema-covered parameters is correct.

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 ("Get most recent messages") and distinguishes itself from semantic retrieval with "without semantic search." However, it never clarifies the messages-vs-mail boundary against the near-identical sibling mail_recent, so an agent still has to guess which of the two recency tools to pick.

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 concrete triggering user phrasings ("recent messages", "latest texts", "what messages did I get"), which is strong positive routing guidance. It omits any when-not condition or explicit named alternative (e.g., use messages_search when the query is topical), leaving exclusions to inference.

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