successes

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only' is redundant. The one genuinely additive phrase is 'the exit code is the verdict,' which hints the result carries a pass/fail determination, though it is unexplained for what is nominally a read of recorded successes. No disclosure of permissions, rate limits, or result shape, but with full annotation coverage the bar is lower.

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 covering scope, parameters, and the read-only/verdict note — no filler. The front-loaded scoping clause is well placed, though the dense jargon makes the first reading slower than the length warrants.

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?

All three parameters are documented and annotations cover safety, but with no output schema the description should carry the burden of describing what is returned ('how each is proved' is asserted but never characterized). The concept of a 'move' and how proof is represented remain undefined, leaving a real gap for an agent interpreting results.

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 the schema already defines `id`, `for`, and `limit`. The description echoes the schema's own mapping ('for' = file, 'id' = one move) rather than adding syntax, format, or interaction detail (e.g. what happens when both are supplied, or that `limit` only affects `for`). Baseline 3 is appropriate.

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 gestures at a specific resource ('the moves that replaced recorded failures') and names the two scoping modes ('for' a file, 'id' for one move), but 'moves' is undefined domain jargon and the verb is only implied. An agent can guess this is a lookup of successful patterns, but it cannot confirm what a 'move' actually is or how it differs from the sibling `failures`/`proof` tools without opening them.

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?

It says which parameters scope the query but never states when to reach for this tool versus `failures`, `proof`, or `steps`. There are no exclusions, no prerequisites, and no mention of the sibling that is the obvious complement (failures), so the agent must infer the choice entirely.

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