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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds behavioral context with 'deterministic signed', implying output is reproducible and cryptographically signed, which goes beyond annotations. However, it does not explain what 'signed' entails, whether authentication is needed, or what the output format is. With annotations doing most of the work, a 3 is appropriate.

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 very short and front-loaded with the tool name, which is efficient. However, 'Durable Agent Task' simply repeats the title and does not earn its place. The rest of the sentence adds some value, so overall it is mostly concise but with a minor 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?

The description is too vague for a tool with one required parameter and no parameter descriptions. It does not explain what a 'durable agent task' is, what 'deterministic signed assessment' means for the caller, or how the 'task' input should be provided. Although an output schema exists and annotations cover safety, the description does not give enough context for an agent to call this correctly, especially given many similar sibling tools.

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 description coverage is reported as 100%, so the baseline is 3. The description adds 'supplied input', which suggests the 'task' parameter is the input being assessed, but it does not clarify the expected structure, format, or constraints of that input. This provides minimal additional meaning beyond the parameter name.

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 says it is a 'deterministic signed assessment over supplied input', which gives a rough sense of the tool's function but lacks a specific verb or clear resource. It does not distinguish itself from sibling tools like 'attest' or 'verify', which could also be described as signed assessments. It is more than a tautology but remains vague about what the tool actually does (executes a task? returns an assessment? creates a durable record?).

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?

There is no guidance on when to use this tool or how it differs from alternatives. No conditions, exclusions, or references to sibling tools are provided. An agent would have no way to decide between this and similar-sounding tools like 'attest' or 'signed_result_comparator'.

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