remember_decision

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

Annotation Contradiction: annotations declare readOnlyHint=true, while the description explicitly says 'Live agent write', routes rows through a review queue, drops low-confidence rows, and persists data. This is a direct contradiction that makes the tool's behavioral contract untrustworthy.

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 dense but every clause earns its place: core behavior, routing rules, dedup/rate-limit, usage timing, sibling alternatives, and return shape. It is front-loaded and avoids filler.

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 the annotation contradiction, the description itself provides the routing behavior, persistence semantics, return JSON shape, and usage context, while the schema covers all parameters. With no output schema, the explicit return shape is a strong addition. The conflicting readOnly annotation prevents a perfect score.

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 100%, so the schema fully documents all 9 parameters. The description adds little parameter-level meaning beyond confirming session-based dedup and rate-limit behavior, which the schema already mentions for session_id. Baseline 3 is appropriate.

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 identifies a specific action ('write into the decision knowledge graph'), the confidence-routing behavior, and explicitly contrasts itself with add_decision and mine_sessions. An agent can distinguish this tool from its siblings without inspecting schemas.

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?

States exactly when to use it ('capture decisions in real time') and names the alternatives for other scenarios: add_decision for manual high-confidence writes and mine_sessions for post-hoc extraction from session logs.

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