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

Annotations already establish this is a non-read-only, non-destructive, non-idempotent mutation. The description adds that reasons 'stay open' and that only a signed-in person may act, which is genuine behavioral context, but it omits idempotency behavior and any return/effect details.

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 short sentences, but the phrasing 'with their words when they give any' is convoluted and the flowery 'Tommo' language reduces clarity. Content is not front-loaded into a crisp lead 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?

For a simple mutation tool with annotations and no output schema, the description covers who may act, what is refused, and the consequence that reasons stay open. However the optional words parameter and the alternative action remain under-explained.

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 50%: offer_id is documented in the schema itself, while words is not. The phrase 'with their words when they give any' implies words is optional commentary, adding modest meaning, but the parameter is not clearly specified.

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 states a specific verb (refuse) and resource (a text change Tommo offered), and the title reinforces it. It is distinguishable from its natural counterpart take_a_text_change by implication, though the sibling is never named 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?

It states a precondition ('Only a signed-in person refuses one'), which is useful context, but gives no guidance on when to refuse versus accept via take_a_text_change, nor any exclusion criteria. Usage is only implied.

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