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

With no annotations, the description carries the full burden and does so well: it states that nothing changes yet, that the change is built on a copy, and that the tool returns before/after plus integrity checks for numbers, dates, and links. It also mentions the proposal_id needed for the next step.

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, each earning its place: the core action, the no-side-effect behavior, and the next-step prerequisite. The most important scoping information is front-loaded in the first 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 tool with no annotations and no output schema, the description covers the essential context: what to do first, what happens during execution, what the result contains, and how to continue. Nothing critical is missing for correct invocation.

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 0%, so the description must explain the parameters. It clarifies paragraph_index (from document_read) and text (full new text), but the optional reason parameter is not explained at all, and no additional constraints or formatting guidance are provided.

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 ('Propose'), a specific resource ('full new text of one paragraph'), and references the source of the index ('paragraph_index from document_read'). It clearly distinguishes this proposal tool from the sibling document_apply, which is the commit step.

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?

The description gives clear workflow guidance: read the paragraph first, propose replacement text, then call document_apply with the proposal_id. It does not explicitly list exclusions or conditions for when not to use it, but the propose-vs-apply distinction is strongly implied and sufficient.

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