Patch managed documentation

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

With idempotentHint=true annotation present, the bar is lower. The description adds genuine value by explaining the optimistic concurrency behavior (write refused on revision mismatch, concurrent edits reported rather than overwritten) and the read-only constraint on indexed repo docs. It doesn't mention the return format or error behavior in detail despite having an output schema, but the annotation plus inline concurrency explanation provide solid coverage.

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 compact sentences that are front-loaded with the primary purpose and mechanism. The second sentence adds a critical safety constraint (read-only indexed docs) without padding. No filler or redundant restatement of the title. Slightly more guidance on return shape could push it higher, but overall it's economical and earns its sentences.

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?

The tool has nested objects and an output schema, so the description doesn't need to explain return values. The description covers the concurrency mechanism, the partial-update behavior, the read-only restriction, and references the move tool for folder changes. This is well-rounded for a patch tool of moderate complexity, though it could mention error responses (e.g., revision conflict handling details) beyond what the schema states.

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 100%, so the baseline is 3. The description adds meaningful context beyond schema: it notes indexed docs are read-only, and it states that only keys present in 'changes' are touched (partial update semantics). The expectedRevision parameter's concurrency behavior is already well-described in the schema itself, so the description's mention reinforces rather than duplicates it. The partial-touch semantics in the description meaningfully complement the schema.

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 'Patch a managed document using optimistic concurrency' — a specific verb+resource with a distinctive mechanism (optimistic concurrency). It also adds important scoping information by noting indexed repository docs are intentionally read-only through this tool. While the sibling project_doc_move is separately named for folder changes, the description doesn't explicitly differentiate from other patch tools like project_card_patch or project_memory_patch, though those target different resource types so the distinction is reasonably clear.

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 states when to use (patch managed docs) and explicitly excludes indexed repository docs ('edit those files directly'), providing a clear when-not. The exclusion is valuable context. However, it doesn't contrast with the sibling patch tools (card, memory, changelog) explicitly, leaving the agent to infer resource-type differentiation, nor does it mention the project_doc_create/list alternatives for creation/listing flows.

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