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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds valuable trail-of-events context: it is immutable, server-attributed, includes old revisions and submitted values, and contains a sensitive warning about internal material. This goes beyond the annotations, though it does not detail pagination limits beyond 25 or auth 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 extremely concise, two sentences, with key facts front-loaded: the count of events, the attributes, and the pagination cursor. Every phrase adds value. The internal-material warning is a high-priority constraint placed at the end but still clear and effective.

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 read-only paginated list tool with only two parameters (one optional) and no output schema, the description covers the essentials: what it reads, how to paginate, and a critical usage warning. It does not explain the output format (e.g., list of events with specific fields) beyond the attributes mentioned, but given the tool's simplicity and annotations, it is adequate.

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%: projectId has a description, but beforeId has none. The description mentions 'beforeId' in passing ('Continue with nextCursor as beforeId') but does not explain its purpose or format beyond that. Given partial coverage, the description adds modest value; it could be improved by explicitly describing beforeId as a cursor from a previous response.

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 states the tool reads 25 immutable dossier change events with specific attributes (server-attributed authors, times, old revisions, submitted field values). It uses a specific verb 'read' and resource 'dossier change events', distinguishing it from related tools like 'list_document_versions' or 'read_document_provenance' by focusing on contribution history.

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 mentions pagination with 'continue with nextCursor as beforeId', which implicitly guides usage. However, it does not explicitly state when to use this tool over siblings or provide alternative tool references. It provides clear context on the nature of the data (immutable events) but lacks explicit exclusions.

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