vault_patch

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

Annotations already declare destructive=true, idempotent=false, readOnly=false, so the safety profile is covered. The description adds genuine value beyond that: the exact-byte ifMatch precondition (optimistic concurrency) and "No automatic retry" — a non-obvious behavioral trait an agent must handle itself. It stops short of describing auth needs or what a failed ifMatch returns.

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?

Four terse sentences, front-loaded with the core action and the ifMatch precondition, with no filler. It is dense but every clause carries information; it is arguably too compressed given the tool's complexity rather than padded.

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 12-parameter, nested-object, destructive mutation with 17% schema coverage, a four-sentence description is thin. Output schema existing means return values need not be explained, but the mutation semantics, parameter behavior, and sibling routing are largely absent, leaving real gaps an agent would hit.

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 17% across 12 parameters with nested objects, so the description must compensate heavily but only touches ifMatch, map-key copying, and heading relative levels. It says nothing about operation, scope, targetType, destination, createTargetIfMissing, or rejectIfContentPreexists, leaving most parameters documented only by their bare enum values.

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 (patch) and concrete resources (heading/block/property), and the ifMatch phrasing signals a conditional partial update distinct from a full write. It is clear on its own but never names or contrasts with siblings like vault_write, vault_append, or vault_move, so an agent must infer the boundary.

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?

"with exact-byte ifMatch from a read/map" implies the prerequisite workflow (obtain the token from vault_read/vault_get_document_map before calling), which is useful implied guidance. However, there is no explicit when-to-use-vs-alternative statement, no when-not guidance, and no routing against the other mutation siblings.

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