edit_annotation

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

No annotations are supplied, so the description carries the full burden and does so: it limits the blast radius (position, shape, dimension length, condition links, quantities and review records unchanged), explains the empty-string clearing behavior, states the RFI-link refusal, and confirms reversibility via one undo_last step. It also explicitly disclaims verdict or human-approval creation, heading off a likely confusion with mark_verdict.

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?

Front-loads the core action, then layers scope limits, refusal condition, and undo semantics in short declarative sentences. No sentence is filler and no information is repeated.

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?

An output schema exists, so return values need not be described. Combined with the disclosed side-effect scope, refusal rule, and undo path, an agent has everything needed to invoke this correctly and to recover from it.

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 100% and both parameters are documented in the schema itself, so the baseline is 3. The description's note that empty text clears the annotation largely restates the schema's 'empty string clears it' and adds no new syntax or format detail.

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?

States specific verbs (shorten, replace, clear) against a specific resource (text of an existing annotation), and explicitly scopes itself away from verdicts and from non-text properties. An agent can distinguish it from edit_condition, link_annotation, and mark_verdict without opening any 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?

Tells the agent where to source the id (list_annotations, not verdicts) and names an explicit when-not case: RFI-linked notes are refused and must be handled in the browser RFI register. That is both a precondition and a routing rule, not implied guidance.

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