describe_acceptance

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds that it can read either a loaded spec or a previously produced verdict, but doesn't state what happens if no spec is loaded or which verdict (last run only?) is returned.

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?

Two tight sentences, front-loaded with the core action, then the mode breakdown. No filler; every clause carries information.

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?

With no output schema, the description usefully describes the shape of each mode's result, and the schema covers the session parameter and its default. Only minor gaps remain, such as behavior when no spec is loaded, but the definition is sufficient to call the tool correctly.

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 coverage is 100% and the schema lists the allowed 'what' values, but the description goes further by explaining what each value returns (summary = name + check counts, checks = full list, last_result = the run_acceptance report). That is genuine meaning beyond the schema's bare enum list.

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 (Read) and resource (the loaded AcceptanceSpec or the last verdict), which immediately distinguishes it from load_acceptance (which loads a spec) and run_acceptance (which executes). It doesn't explicitly call out the siblings it is not, but the read-only framing is unambiguous.

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?

Usage is implied: you call it to view the loaded spec or the most recent verdict. However there is no explicit when-to-use guidance or routing to alternatives (e.g. 'use this instead of run_acceptance when you only want to inspect'), so the agent must infer the context.

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