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

Adds substantial behavior beyond the annotations: omitted fields preserve earlier values (so partial progress reports are safe), a duplicate name on another issue is refused with that issue's key, editing permission is required, 'starting' is normalized to running, and the response carries 'created' and 'stateBefore'. This is exactly the kind of context annotations cannot express.

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?

Purpose is front-loaded and every sentence carries information, but the prose is long and clause-heavy, mixing scope, idempotency, enum semantics and auth into one block. Dense rather than padded, so a 4 rather than 5.

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 15-parameter mutation with no output schema, the description covers identity semantics, partial-update behavior, error and permission conditions, and the shape of the response. An agent has everything needed to invoke it correctly on first try.

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 already 100%, so the baseline is 3; the description nonetheless adds real semantics — the state vocabulary, the 'starting' alias not present in the schema, why commit + repository make results checkable, and the Markdown/$…$ format for 'result'. It stays above baseline without restating every field.

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?

Opens with a specific verb and resource — reporting how a computation an issue rests on stands — and scopes it with concrete examples (GAP run, batch of work units, remote Lean build) plus the clarifying 'the tracker runs nothing'. That distinguishes it from list_computations/delete_computation without opening a schema.

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 a clear when-to-call rule: on submission, as it progresses, and at the end, always with the same 'source' + 'externalId' because that is one job, updated. The when-not ('never a second') is implicit rather than a named sibling alternative, which keeps it just below a 5.

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