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

With no annotations provided, the description carries the full disclosure burden. It thoroughly covers storage defaults (nothing stored), save behavior (what gets stored, report_url, 30-day freshness), observations and their non-effect on verdict, suggested criteria reuse, delete_credential, and privacy guarantees (never stores file content, filenames, source_context; removes glossary strings). This is exemplary behavioral 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 about 120 words but packs every sentence with unique information: purpose, default storage behavior, save flow, observations, suggested criteria, deletion, and privacy. It front-loads the core function ('Privately check a received delivery') and then logically orders the behavioral details. No filler or redundancy is present.

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?

The tool has 11 parameters, multiple alternative input modes, and a rich save/report flow, yet the description explains the essential context: what the tool does, what a report includes, observations external to criteria, how to convert suggestions into enforceable checks, and privacy guarantees. The schema covers the 4.4 MB size limit and individual parameter formats, so nothing critical is missing.

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 82%, above the 80% threshold, so the baseline is 3. The description adds value by explaining the conceptual roles of the alternative criteria inputs (template_id, need, criteria, contract_id, report_token) and how they relate to one another. It also clarifies the 'save' parameter's downstream effects. This goes beyond the schema's basic descriptions, earning a 4.

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 opens with a clear, specific verb phrase: 'Privately check a received delivery against' followed by the full set of accepted criteria sources (template, plain-word requirements, machine checks, contract, report_token). It distinguishes this tool from siblings by focusing on the act of checking received work, not on bounty management, sourcing, or registration. The title is also unambiguous.

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 clearly implies the primary use case: when a delivery is received and needs to be checked against predefined criteria. It also explains the different ways to provide criteria and the save option. However, it does not explicitly name sibling tools or state when NOT to use this tool, so it stops short of a full 5.

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