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

The description adds substantial behavioral detail beyond annotations: it states 'No LLM call — deterministic' (confirming annotations), explains error detection heuristics in depth (error markers, status fields, text prefixes), notes that 'Model prose is never scanned for keywords', and warns that a trace parsing to 0 steps is flagged. This exceeds the readOnly/idempotent hints and provides actionable transparency.

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 dense paragraph that efficiently packs key information: input formats, assertion types, error detection, outputs, and usage intent. It is not overly verbose for the complexity it covers, though it could be broken into bullet points for readability. It earns its place without fluff.

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 complex input (trace) and seven assertion types, the description is comprehensive. It explains error detection behaviors, return values (per-assertion PASS/FAIL, parsed steps, warnings, verdict), and a caution about empty traces. With an output schema present and annotations covering safety, the description leaves no significant gaps.

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 baseline is 3. The description adds meaning by explaining error detection logic and assertion semantics beyond the schema's brief field descriptions, such as how 'errored' is determined and that warnings are returned. This enhances understanding of the 'trace' and 'assertions' parameters.

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 the tool runs declarative assertions on an agent trace, enumerates supported trace formats (OpenAI, Anthropic, LangChain, ReAct) and lists specific assertion types (order, must_call, etc.). It distinguishes from siblings by focusing on agent trajectory validation rather than generic validation tools like validate_email or validate_url.

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 explicitly says 'Use this to gate CI/CD on agent behavior correctness', providing a clear use case. It doesn't name specific alternatives, but the purpose is distinct from other validate* tools, and the context is sufficient for an agent to select it.

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