update_profile

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

With no annotations provided, the description carries the full behavioral burden and delivers: it flags the mutation semantics ('UPDATE-only'), discloses the failure mode (error if profile absent), lists immutable fields (use_count/created_at/created_by/id stay unchanged), and warns about a type-specific config constraint (SQLite: don't pass config.filePath). It does not cover return shape or permissions, but the disclosed behaviors go well beyond baseline.

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, each earning its place: purpose, error behavior, immutable fields, and a platform-specific gotcha. The core purpose is front-loaded first and the '[group: profiles]' tag is bracketed at the end. No filler or repetition of schema content.

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 complex tool with 8 parameters, nested config, two enums, no output schema, and no annotations, the description covers the essential contract: update-only semantics, error behavior, immutable fields, and a critical config constraint. Gaps remain — how the target profile is identified (name is required but never stated as the key), what the tool returns, and per-field semantics — but the description is well above minimum viable for this complexity.

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%, so the description must compensate, and it partially does: it adds the only parameter-level guidance available ('SQLite 类型不要传 config.filePath'), implying config is type-sensitive, and reveals that use_count/created_at/created_by/id are not updatable. However, seven of the eight schema properties (name, role, tags, enabled, description, permissionMode, and general config contents) receive no semantic explanation, leaving a significant gap.

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 opens with a specific verb+resource+scope: '修改已存在的 profile(UPDATE-only)' (modify an existing profile, update-only), which unambiguously identifies the operation. The error condition ('profile 不存在抛错') reinforces that it targets existing records, cleanly separating it from the sibling create_profile without needing schema inspection.

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 clearly states this is for modifying existing profiles and that a missing profile causes an error, which implicitly tells the agent to use create_profile for new records. However, it never names the alternative tool explicitly or states a when-not-to-use condition, so the routing is inferred rather than explicit.

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