anon_patch_custom_tools_tool_id

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds genuinely new behavioral context beyond those: the required authorization scope, that the update is partial/merging, and that validation rules mirror creation. It does not discuss reversibility of overwritten fields or any rate limits, keeping it below 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?

Four short sentences, front-loaded with the action and permission requirement before the endpoint detail. Nothing is padded, though restating the PATCH URL template alongside the tool name is mildly redundant.

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 single-resource PATCH with full annotation coverage and no output schema, the description covers the essentials: permission scope, partial-update semantics, and the projectId scoping rule. The remaining gap is body-field documentation, which is a meaningful but not fatal omission for this tool class.

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 0%, and the nested body contains six undocumented properties (url, mode, name, scopes, passToken, description). The description only clarifies one path-level point — that projectId is unnecessary — and gestures at 'validation same as creation' without explaining any body field semantics, leaving the agent to guess what the payload accepts.

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 states a specific verb and resource — '更新自定义工具' (update custom tool) — and is clearly distinct from sibling create/read/delete custom-tool tools (anon_post_custom_tools, anon_get_custom_tools, anon_delete_custom_tools_tool_id). The PATCH path is included, confirming the exact operation.

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 gives real usage conditions: a required 'tools:manage' scope, the fact that this is a partial update rather than a replacement, and that projectId must NOT be supplied because the project is derived from the API key. It does not explicitly contrast itself with the sibling POST create tool, so it stops short of a 5.

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