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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description adds real value beyond them: the 25-event page size, the immutability of the events, server-attributed (non-spoofable) authorship, and the critical handling constraint that the material is internal and must never be delivered to buyers.

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?

Two sentences, no filler: the first defines the resource and payload, the second handles pagination and the handling restriction. The most decision-relevant information (what is returned) is front-loaded.

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?

With no output schema, the description carries the return-shape burden and does describe the event fields and the cursor reasonably well, plus a safety caveat. It stops short of stating the scope of the history (e.g. per project vs per contributor) or whether results are strictly ordered, which would complete the picture for a two-parameter paginated reader.

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 only 50% (beforeId has no schema description), and the description compensates by explaining that the cursor comes back as nextCursor and should be passed back as beforeId for continuation. It does not add meaning for projectId, which the schema already documents.

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 a specific verb and resource ('Read ... dossier change events') and enumerates the payload contents (authors, times, old revisions, submitted field values) plus the page size of 25. It is clearly distinguishable from write-oriented siblings like submit_draft or request_contribution_review, though it never names a sibling for differentiation.

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 implies the read/audit use case and gives pagination mechanics ('Continue with nextCursor as beforeId'), which is genuinely actionable. However, there is no explicit when-to-use/when-not-to-use statement and no alternative tool is named for related needs such as reviewing or assembling contributions.

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