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

Annotations already declare idempotentHint=true and destructiveHint=false, so the description doesn't need to repeat those. It adds value by specifying that unchanged fields are preserved (a merge semantics), which is not inferable from annotations. It also mentions idempotencyKey, reinforcing the idempotent nature. The description does not contradict annotations; it complements them with merge behavior specifics.

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 description is a single, compact sentence that front-loads the most important information: the action, the resource, and the key concurrency parameters. Every word is necessary, with no fluff. It avoids repeating schema details and only highlights the behavior that matters for correct invocation.

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?

Given the tool's complexity (12 parameters, nested objects, no output schema), the description is too brief. It doesn't explain the fields that can be updated (e.g., body, title, outcome) or how attachment replacement works (by id or data), nor does it state that updated fields are replaced wholesale. The merge behavior is clear, but the exact semantics of each updatable field are not disclosed. The description relies heavily on the schema, but with only 8% coverage, it should do more to clarify how to provide values for the various fields.

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 only 8%, meaning the description is nearly the only source of parameter semantics. It explicitly mentions expectedVersion and idempotencyKey, which are critical for concurrency and retry safety. It also implies that body, title, summary, outcome, etc., are the fields being updated. For the many other parameters (attachments, sessionId, executionId), it doesn't explain them, but the schema provides structural details, so the description adds high-level semantics that the schema lacks, partially compensating for low 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?

The description clearly identifies the action (update), the resource (authored report fields), and explicitly notes that existing paragraphs and untouched fields are preserved, indicating a merge operation. It distinguishes from create_report by specifying it's an update. The inclusion of expectedVersion and idempotencyKey in the first sentence signals this is a concurrency-controlled update, which adds specificity beyond a generic 'update report'.

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 states the tool is for updating authored report fields, implicitly indicating when to use it (when an existing report exists and needs changes). It does not explicitly mention alternatives like create_report for new reports or list/read tools for viewing, but the purpose is clear enough for an agent to infer this is not the tool for initial creation. The mention of preservation of untouched fields gives a hint of the behavior, but no explicit 'use this instead of X' guidance.

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