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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description earns credit by explaining why that is coherent: the tool only produces unsigned transactions 'simulated from the wallet' that the owner must sign. It adds real behavioral detail beyond the annotations — revocation is effective at once for commits and cancels, and the keys' orders stop filling from the next batch. It omits gas/submission mechanics for the resulting transaction.

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?

Front-loaded with the output artifact ('Unsigned transactions for the owner's wallet'), then the two modes, then the effect. Dense but every clause carries information; the telegraphic phrasing ('Effective at once for commits and cancels') is compact rather than padded.

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 3-parameter preparation tool with no output schema and full schema coverage, the description supplies what an agent most needs: what it returns, the two revocation modes, and the immediate effect on live orders. The remaining gap is handling of the optional agent_id versus all combination, which neither description nor schema resolves.

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 all three parameters are already documented in the schema, making 3 the baseline. The description reframes 'all' as 'the kill switch' and ties agent_id to a single session key, but adds no format, precedence, or conflict rules (e.g., what happens if both agent_id and all are supplied).

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?

States a specific verb and resource ('revoke one session key (agent_id) or every live one') and immediately clarifies that the output is unsigned transactions for the owner's wallet, not an executed revocation. It does not explicitly name or contrast the counterpart sibling darkroom_session_register, so it stops short of full sibling differentiation.

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?

Gives clear selection context between the two modes: pass agent_id to revoke one key, or 'all: true, the kill switch' to revoke every live key. It does not state any when-not-to-use condition or point at an alternative tool for the same job, so there is no exclusion guidance.

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