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

Annotations provide readOnlyHint=true and destructiveHint=false, but the description adds critical context: it explicitly states what it does NOT do (quality assessment) and clarifies it is non-destructive and stateless ('Nothing is stored'). This goes beyond the annotations, setting clear expectations without contradicting them.

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 three sentences, each earning its place: it instructs on inputs, explains the output, and clarifies limitations and data handling. It is efficient, front-loaded with the core purpose, and avoids redundancy.

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 read-only validation tool with a relatively simple input schema and no output schema, the description covers the essentials. It explains what the tool checks (shape, not quality), the input requirements, and lack of persistence. It leaves out specifics like the exact format of the output (e.g., what 'reports' means in terms of response structure), but this is minor given the tool's simplicity and annotations.

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 input schema descriptions are already quite detailed (e.g., 'keys: tension, cost, falsifier, human_knowledge, and optionally directive-1..7'). Since schema coverage is 100%, the description's value is minimal but non-zero: it frames the parameters as part of the 'shape' check, implying that the answers object must have those specific keys. This aligns with the schema, but adds no extra syntax or format detail.

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: it checks the shape of the user's answer and resolution against required elements. It explicitly distinguishes from quality checking ('cannot tell you whether your answer is right'), and the name 'deliberate_check' implies it verifies the deliberate reasoning process. This is distinct from siblings like 'verify_attestation' or 'get_covenant'.

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 when to use it: after providing an answer and resolution, to check if any directives were skipped. It does not explicitly name alternatives or exclusions, but the phrase 'This reports what you skipped' gives clear context. Given the tool's niche (checking completeness of reasoning), this is adequate without explicit when-not guidance.

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