op_update_document

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

Annotations only declare readOnly=false, openWorld=true, idempotent=true, destructive=false. The description adds critical behavioral detail beyond those flags: the description field replaces the entire markdown body, concurrent edits are last-write-wins with no locking, and the {'raw': ...} form corrupts stored text while a plain string is the safe format. This is exactly the kind of context an agent needs before invoking the tool.

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?

Three dense sentences, with the core action and scope front-loaded. Every sentence earns its place: the replacement semantics, the concurrency/locking caveat, and the serialization pitfall are all actionable and non-redundant with the schema or annotations.

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 three-parameter mutation tool with no output schema and simple annotations, the description covers the key hazards an agent must know: whole-body replacement, last-write-wins concurrency, and the correct string format for description. Nothing essential to calling the tool correctly is missing.

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?

The schema already documents title and description with 67% coverage. The description adds value by clarifying that title and/or description can be updated and by warning that the description parameter must be a plain string, not the {'raw': ...} object used elsewhere. It does not add meaning for the id parameter or title max-length beyond what the schema already provides, so it stops short of a 5.

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 ('Update a document') with a clear scope ('title and/or description'), and further clarifies that the description replaces the whole markdown body. It also contrasts documents with work packages, which distinguishes it from the sibling op_update_work_package even without reading that tool's 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?

The description gives clear operational context: it is for updating document title/description, and it explicitly notes that unlike work packages, documents have no lockVersion and are last-write-wins. This effectively warns against expecting optimistic locking and points to the work-package tool as the one that has it, though it stops short of explicitly naming the alternative tool for work-package edits.

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