search_logs

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

With no annotations, the description carries the full burden. It discloses that the search operates over a 'recent window' and implicitly that it searches across all streams. However, it doesn't specify read-only behavior, pagination, or what the return format looks like. For a search tool, the lack of explicit safety statements is a minor gap, but the description does add some behavioral context beyond the schema.

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 a single, front-loaded sentence that states the purpose and the usage condition in a compact manner. There is no fluff, and the critical information (what it does and when to use it) is presented immediately.

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 tool has 4 parameters (all documented) and no output schema, the description should ideally mention what the tool returns (e.g., a list of matching events) and any relevant constraints. It mentions 'recent window' but doesn't clarify whether results are sorted or how pagination works. While the core usage is clear, the lack of return-format details leaves an agent uncertain about the response structure. This is a moderate gap.

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%, so the baseline is 3. The description adds no parameter-specific detail beyond the schema, but it does provide example usage ('an exception, an order id, a URL') that helps an agent understand what 'contains' is meant to match. This adds a bit of value but does not fully compensate for the lack of any parameter semantics in the description itself.

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 uses a specific verb+resource: 'Find events matching text across the recent window.' It clearly states the action and scope, and the usage hint ('but not which stream it is in') distinguishes it from stream-specific tools like list_streams or tail_logs. This is a clear, non-tautological purpose.

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 provides an explicit condition: 'use when you know what the message says... but not which stream it is in.' This tells the agent when to choose this tool over alternatives, though it doesn't name specific sibling tools or explicitly state when NOT to use it. Still, it gives a clear decision rule.

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