deed_review

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

Since no annotations are provided, the description carries the full transparency burden. It explicitly states that the operation is in-memory ('Both sides stay in memory'), has no file access ('opens no file'), holds no capability, and that the policy verdict is 'evidence, not a transport error.' This is strong behavioral disclosure, though it does not cover all possible failure modes or side-effect details.

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 four sentences, front-loaded with the primary purpose, and every sentence adds meaningful detail: purpose, output, policy behavior, and memory/safety characteristics. There is no filler or redundant 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?

Given the tool has moderate complexity (before/after arrays plus a nested policy object), no output schema, and no annotations, the description covers the key aspects: input comparisons, return receipt content, policy semantics, and absence of side effects. It does not detail the exact JSON receipt structure or explain array correspondence, but it is sufficient for an agent to invoke and interpret results at a high level.

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% (before/after arrays and policy object fields are all described). The description adds contextual meaning around the policy object (its verdict is evidence, not an error), but mostly restates what the schema already provides. Baseline 3 is appropriate 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 a specific verb ('Compare') and a resource ('the checked module set before a patch with the set after it'), making the core action clear. It also specifies the output ('one JSON review receipt') and distinguishes this from sibling tools like deed_check or deed_run by focusing on before/after patch comparison.

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 establishes the use case: comparing module sets before and after a patch. It does not explicitly mention when not to use the tool or name alternatives among the sibling tools, so it stops short of full guidance, but the context is unambiguous enough for an agent to decide on appropriate usage.

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