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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that it returns recent requests and can be filtered. It does not mention whether it is read-only, the output format, pagination, or any error conditions. For a tool with no output schema, this is a significant gap.

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 sentences, zero fluff, with the core purpose front-loaded and a natural workflow transition. Every word earns its place.

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?

Despite the concise nature, the description omits critical operational details. There is no output schema, so an agent does not know what fields are returned (beyond an id for phpray_trace), whether results are paginated, or what happens when filters yield nothing. For a 5-parameter tool, this is insufficient for confident invocation.

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 semantic weight by suggesting min_ms and status are used to 'find the bad ones,' which hints at slowness and error filtering beyond the schema's dry descriptions. This is a meaningful addition.

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 clearly states 'Recent requests for a site' – a specific resource and action. It also mentions filtering by min_ms and status, and points to phpray_trace for a detail view, effectively differentiating itself from that sibling. The purpose is unmistakable.

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?

It provides a concrete use case: 'Filter with min_ms and status to find the bad ones' and a workflow pointer: 'then pass an id to phpray_trace.' This tells an agent when to use this tool (to list/filter requests) and that phpray_trace is for individual traces. It lacks explicit exclusions for other siblings like phpray_errors, but the guidance is adequate.

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