Search messages

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

Discloses that it reads the local Teams cache, not the full server archive - a critical behavioral trait. No annotations provided, so this is valuable context.

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 sentences with no redundancy: purpose, parameter hints, and behavioral note. Efficient and front-loaded.

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?

Covers purpose, key parameter usage, and the local cache limitation. Missing output details but acceptable given no output schema. Adequate for a search 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?

With 50% schema description coverage, the description adds meaning for from/in and mentions_me, but leaves many parameters (since, until, kind, etc.) without additional explanation beyond the schema.

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 'full-text search across all messages with filters' and distinguishes from siblings like read_messages. The empty query behavior as filtered browse adds specificity.

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?

Provides explicit guidance on empty query, from/in usage with substrings/handles, and mentions_me flag. Lacks explicit when-not-to-use vs siblings, but context is clear.

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