failures

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

Annotations already cover read-only, idempotent and non-destructive, and the description partly repeats 'Read-only'. What it adds beyond annotations is 'the exit code is the verdict' — the agent learns the tool reports through exit status rather than content, plus that each entry carries the guard that stops the mistake. Return shape is only sketched.

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?

Three tight sentences, front-loaded with what the tool returns before the scoping requirement. Dense domain jargon ('shapes', 'tells', 'guard') costs some readability but nothing is padding.

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?

There is no output schema, so the description is the only source of return-shape information, and it only says entries come 'with the guard that stops it' plus an exit-code verdict. Given four parameters, a default `limit`, and no annotations about payload format, an agent still cannot predict what an entry looks like.

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 documents all four parameters, and the description largely restates those meanings (file for `for`, error text for `match`, one shape's `id`). The `limit` parameter and its default of 3 are never mentioned in the description, so it adds no meaning the schema doesn't already carry.

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 names a concrete resource (recorded agent mistakes with their stopping guard) and the two scoping axes (file via `for`, error text via `match`). It also states what the tool does NOT do ('the whole ledger is not offered'). It never names the obvious counterpart `successes`, so sibling differentiation is left to the agent's inference.

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 tells the agent it must scope results with `for`, `match` or `id`, which is implied usage guidance, but gives no when-to-use/when-not framing and no comparison to siblings like `successes` or `proof`. The one exclusion is about scope, not about tool selection.

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