anon_post_custom_tools

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, so the write/mutation profile is covered structurally. The description adds genuinely new behavior: the 400 invalid_url failure mode for non-http(s)/unresolvable URLs, silent filtering of out-of-range scopes, and the mode default — all beyond what annotations provide.

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?

Extremely dense and front-loaded: purpose, permission, then per-field constraints separated by semicolons, closing with the endpoint and the non-obvious projectId note. No filler 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?

For a create tool with no output schema, it covers the essentials an agent needs: required fields, permission gate, validation limits and failure mode, defaults, and the project-scoping gotcha. It omits the passToken default (present only in schema) and gives no hint about the created resource's identity in the response, which is a minor gap.

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?

It adds meaning beyond the schema for most fields: name ≤50, url protocol/length bounds plus the exact error code, description ≤200, mode default embed, and the notable silent-filtering semantics of scopes (schema only says illegal items are dropped, description says supersets are filtered silently). passToken is left unmentioned, so it falls just short of complete coverage of the body fields.

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+resource ("创建自定义工具" / create custom tool) and the description's endpoint line (POST /api/projects/{id}/custom-tools) confirms it. It is cleanly separable from siblings get_custom_tools, patch_custom_tools_tool_id, and delete_custom_tools_tool_id.

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 surfaces a prerequisite ("需 tools:manage 权限") and clarifies that projectId must not be passed because the project derives from the API key, which is useful invocation context. However, it never states when to use this versus alternatives (e.g. patching an existing custom tool) or any when-not condition, so guidance remains implied.

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