tool_stats

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

No annotations are provided, so the description carries the full behavioral burden. It never states the aggregation window, whether results are global or scoped to a trace, what the sort order or tie-breaking is, or that the operation is read-only. Read-only can only be guessed from 'rank'.

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?

A single sentence with the verb, resource, and ranking dimensions front-loaded. There is no filler, no restatement of the tool name, and every word carries information.

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?

An output schema exists, so return values need not be described. However, with three parameters at 0% description coverage and zero annotations, the definition is only minimally viable — an agent could call it with defaults but would not know how to scope or limit the query correctly.

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 0% for three parameters. The description mentions no parameter at all: limit (result cap), trace_id (scope to one trace), and tool_name (restrict ranking to one tool) are undocumented in both schema and prose. 'Rank tools' loosely gestures at the tool dimension but does not explain that tool_name filters it.

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?

Names a specific verb (rank) plus the resource (tools) and the four ranking dimensions (errors, denials, latency, call volume), so the agent knows exactly what comes back. It does not, however, distinguish itself from overlapping siblings like failure_report or slowest_spans, which cover adjacent slices of the same data.

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 purpose clause 'to find unhealthy integrations' implies a diagnostic use case, but there is no explicit when-to-use, no when-not-to-use, and no pointer to alternatives such as failure_report for error detail or slowest_spans for latency detail. Usage is inferable but not guided.

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