prepare_attested_computation

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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds valuable context: 'non-executing' clarifies the tool does not run the computation, and 'without echoing parameter values' highlights a privacy and security behavior not evident from annotations. This goes beyond the structured hints.

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 a single, focused sentence that begins with the action and states the key output. Every word contributes meaning; there is no fluff or verbosity.

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?

Given the moderate complexity, no output schema, and annotations covering safety/idempotency, the description adequately covers the tool's purpose, its non-executing nature, and its privacy behavior. It lacks details on output format or freshness evaluation, but those are secondary and partially captured by the schema's 'asOf' parameter.

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 100%, so parameters are already well documented. The description's mention of 'declared parameters' aligns with the schema's 'keyed only by declared names', but adds no new syntax or format details. It earns the baseline 3 because the schema does the heavy lifting.

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 uses specific verbs 'Check' and 'produce', names the resource 'Attested Computation', and clearly states the output ('non-executing digests'). This distinguishes it from sibling tools like inspect_attested_computation by emphasizing that it prepares rather than inspects and that it does not execute.

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 when one needs to validate declared parameters and obtain a digest without executing the computation. However, it does not explicitly state when to use this tool over alternatives like inspect_attested_computation, nor does it mention any exclusions or prerequisites.

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