Trace diff

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

Annotations already declare the safe read-only, idempotent, non-destructive profile, so the bar is low. The description goes beyond them by disclosing the exact result shape (p95 and error rate before/after, per-span latency share, an example trace ID), which is valuable since no output schema exists.

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?

One dense sentence with a front-loaded subject and a colon-delimited list of returned fields; nothing is wasted. It is a noun phrase rather than a verb-first statement, which slightly weakens immediate readability but not materially.

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?

With no output schema, the description carries the return-value burden and does so well, and all six parameters are fully documented in the schema with annotations covering the safety profile. The only real gap is the absence of routing guidance among sibling tools.

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 100%, so every parameter is already documented with formats, defaults, and examples. The description only restates the baseline concept and adds no syntax or constraints beyond the schema, so the baseline 3 applies.

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 analysis: span names that regressed in latency or error rate versus a baseline, plus the returned metrics. It clearly identifies the resource (spans) and operation (diff against a baseline), though it never names the siblings it should be preferred over.

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?

Usage is implied by the phrase 'compared with a baseline' and the regression framing, which tells an agent this is for finding performance/error regressions. However, it offers no explicit when-to-use rules and does not distinguish itself from what_changed or new_errors, which an agent must infer.

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