find_slow_traces

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

With no annotations, the description carries the full burden, and it responsibly discloses a key behavior: if no tracing provider is configured, the tool returns guidance instead of actual traces. This goes beyond the surface meaning and helps set expectations, though it doesn't specify what the guidance contains.

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 core purpose first and appends the caveat in parentheses. No filler words or redundant phrases.

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?

The tool has no annotations, no output schema, and 5 parameters, but the description does not explain expected return format, possible values of 'guidance', or the semantics of limit and min_duration_ms. An agent would need to call it blindly or rely on the schema, which is not sufficient for a complex 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?

The description adds little beyond the schema. It mentions 'for a service', which duplicates the service parameter description, and 'slowest' hints at ordering, but does not explain limit, window, min_duration_ms, or namespace. With schema coverage at 60% and no descriptions for some params, the description doesn't compensate for the undocumented ones.

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 states a specific verb-resource pairing: it returns the slowest traces for a given service from the tracing provider. It also communicates the current state (none configured), which makes the tool's behavior clear even if siblings are not explicitly named.

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?

There is no guidance on when to choose this tool over siblings like get_trace or diagnose_slow_requests. The parenthetical about returning guidance is more of a behavioral caveat than a usage rule, and no conditions or exclusions are provided.

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