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

With no annotations present, the description fully carries the behavioral transparency burden and does so excellently. It discloses default non-storage, what happens when save is true, the report contents, the presence of observations with suggested_criterion, the one-time delete_credential, and strong privacy guarantees (file content, filenames, and verbatim source_context never stored).

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?

Although the description is lengthy, every sentence contributes unique behavioral or usage information. It front-loads the primary purpose, succinctly explains the save flow, report contents, observations, and privacy, and avoids redundancy with schema definitions. There is no filler or repetition.

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?

For a complex tool with 11 parameters and no output schema, the description is impressive. It covers the main behavior, save semantics, report contents, and privacy. It could be more complete by explicitly describing the full response structure or giving composite use cases for the oneOf branches, but it already covers the essential user-facing aspects.

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 schema covers 82% of parameters, so the baseline is 3. The description goes beyond schema by explaining the functional semantics of key parameters: how report_token preserves criteria structure, how source_context is needed for reruns, and how suggested_criterion sentences can be pasted into 'need' verbatim. This adds meaningful value beyond the schema's field-level descriptions.

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's purpose: 'Privately check a received delivery against a template, plain-word requirements, explicit machine checks, a saved contract, or a saved report_token.' It uses the specific verb 'check' with resource 'received delivery' and names the criteria sources, distinguishing itself from sibling tools like submission_post or source_report.

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 implies usage by explaining what the tool checks against (templates, plain-word needs, criteria, contracts, report tokens), but it does not explicitly state when to use it versus alternatives or include exclusion criteria. This provides clear context without formal alternatives, aligning with a 4 rather than a 5.

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