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

The description states plainly that the pull and its unpromoted rows are deleted, yet annotations declare destructiveHint=false, which asserts the tool performs only additive updates. That is a direct conflict an agent relying on annotations would resolve incorrectly. The effect disclosure itself is otherwise unusually rich (promoted rows kept and returned, hash reusable), but it contradicts the declared hint.

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?

The core action is front-loaded, which is good, but the same idea is restated three times ("so it can be re-read and staged again", "handed over again from a fresh read", "The hash is free again afterwards"), and the trailing "Effects:" line duplicates the opening sentence.

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 still tells the agent what comes back (promoted rows are "listed back") and what survives the operation. Missing only an explicit statement of the failure modes (e.g. what happens if the pull id is unknown or rows are already promoted beyond the listed case).

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?

Both required parameters are fully documented in the schema (reason: "Why — the wrong file, a misread column, a re-pull."; source_id: "The pull, e.g. PUL-0001."). The description adds only the requirement that a reason accompany the discard, not new syntax or validation rules. Baseline 3 applies at 100% coverage.

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?

Specific verb and resource: "Throw out one staged pull and every unpromoted row from it, with a reason." The scope (pull + unpromoted rows only) is precise enough to distinguish it from pros_promote and pros_rows, though it never names those siblings explicitly.

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?

"A wrong pull means a wrong file: staged rows are never edited, the pull is discarded and handed over again from a fresh read" gives a clear triggering condition and explains the correct workflow (discard then re-stage rather than editing). No explicit when-not guidance or named alternative (e.g. inspect with pros_rows first) is given.

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