proveit_progress

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

With no annotations, the description carries the full burden and does disclose meaningful traits: the data is local-scope only, it contains timestamps and read counts, and it deliberately excludes any qualitative assessment. The main gap is that 'local' is left undefined (local machine vs. local to the workspace) and no access or rate-limit context is given.

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 short sentences with the scope constraint front-loaded ('Local progress only') and no filler. The trailing clause about the season closing is slightly indirect and relies on undefined jargon, but it earns its place by explaining the absence of performance data.

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 zero-parameter read with no output schema, the description covers both the returned content and the notable exclusion, which is what an agent needs to choose it correctly. It does not explain the response shape or ordering, but the tool's simplicity makes that a minor omission.

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?

The tool takes zero parameters, so the schema baseline is 4; there is nothing for the description to disambiguate. The description correctly implies a parameterless, no-argument call.

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 the resource precisely: locally recorded progress, specifically which tasks were submitted and when, plus a count of proofs read. It implicitly distinguishes itself from reporting siblings by insisting it 'never says how well you are doing', though it never names an alternative tool outright.

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 gives a clear usage boundary — use this for your own submission/reading activity, not for performance evaluation — and explains that evaluative data does not exist yet ('nothing of the kind exists before the season closes'). It stops short of naming the sibling tool to use instead when the agent does want a performance view.

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