Metis — Update Thinking Profile

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

Without annotations, the description discloses the key behavioral trait: it writes to system/thinking-profile.yaml. It also notes safety for repeated calls, indicating no destructive side effects. The mutation is clear, and no contradictory information is present.

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?

The description is concise: two short paragraphs, first stating purpose, second listing computed fields in a bullet-like style. No unnecessary words, and the key information is front-loaded.

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?

Despite having an output schema (not shown but signaled), the description does not mention what the tool returns (e.g., success message or updated profile). However, the computed fields are well-described. A brief note on return value would improve completeness.

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?

The input schema is empty (0 parameters), so schema coverage is 100%. The description adds meaning by explaining what the tool computes, but does not need to elaborate on parameters. Baseline is 4 because no parameter documentation is required.

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 the tool recomputes and updates the thinking profile from the last 90 days of events, listing three computed components (connection_preferences, preferred_idea_sources, agent_feedback). This distinguishes it from siblings like get_thinking_profile (read-only) and reset_thinking_profile (reset to default).

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?

The description says 'Safe to call multiple times,' implying idempotent usage, but does not explicitly state when to use this tool vs alternatives (e.g., reset_thinking_profile, get_thinking_profile). Guidance is minimal and implicit.

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