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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context: what ground truth is compared against, and the response shape (per-check pass/fail/warn, 0-100 confidence, critical failures). Auth requirements, rate limits, and behavior when no report exists are still undisclosed.

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?

Front-loaded with the verb and purpose, then a compact enumeration of check categories, then the usage trigger. The long middle sentence is dense but each item earns its place by telling the agent what validation coverage to expect.

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 a rich annotation set, a single fully documented parameter, and an output schema present, the description supplies everything needed: purpose, workflow position, validation scope. Only minor gaps remain, such as prerequisites (does a report for the ticker need to exist first?) and handling of missing data.

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?

One parameter with 100% schema description coverage ('ticker': 'NZX ticker symbol'), so the schema already does the work; baseline 3 applies. The description implicitly clarifies that only a ticker is needed rather than the report body, but adds no format or scoping detail about the parameter itself.

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?

Specific verb+resource: 'Validate a deep research report against ground-truth NZXplorer data', followed by an explicit inventory of what is cross-checked (revenue/NPAT, GRS, M/F/Z-scores, director counts, ESG, thesis structure). This distinguishes it from siblings like get_deep_research (which generates) and check_thesis (which checks a narrower artifact).

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?

Gives a clear trigger: 'Use after generating a deep research report to verify accuracy before sharing.' It places the tool in a workflow, but names no alternatives and no when-not conditions (e.g., what to do if no report exists yet). Solid context, no exclusions.

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