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

Annotations already establish it is a non-readonly, idempotent, non-destructive mutation. The description adds real behavioral context beyond that: the source/quotation is rechecked for immutability, only selected evidence is stored, a new context revision is returned, and no human approval is granted. It does not spell out the failure/rejection behavior of the recheck, keeping it short of a 5.

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?

Five tightly packed sentences, front-loaded with the action and followed by constraints and workflow. Each sentence contributes information, though the density makes it slightly hard to scan.

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?

No output schema exists, so the description does partially compensate by explaining that a new context revision is returned and must be re-read. However, for a 7-parameter nested mutation with 29% schema coverage, it leaves much of the input contract and any error handling unaddressed.

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 29% across 7 required, largely nested parameters, so the description carries the burden. Its only parameter-relevant statement is 'Consecutive fragments must belong to the same unit', which touches fragmentIndexes semantics but leaves projectId, sourceKey, pageRevision, contextRevision, and expectedReadRevision unexplained.

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: 'Add exact selected quotations ... to the dossier citation catalog.' This is clearly distinct from siblings like contribute_dossier or add_evidence_version, though it never names an alternative to differentiate itself. Purpose is unambiguous.

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?

Provides some procedural guidance ('do not submit paraphrases', 'read its catalog, then submit or refresh analysis before contributions/review'), which implies the workflow phase. However, it never states when to prefer this tool over siblings or what the preconditions are for calling it.

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