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

Goes well beyond the annotations: append-only, hash-bound, single-write-per-decision, and the important disclosure that omitted cost/latency/energy are recorded as explicitly unknown rather than inferred. Consistent with idempotentHint=false, but it stops short of stating the failure mode on a duplicate write.

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?

Three tight sentences, front-loaded with the core action, then the optional-field semantics, then the uniqueness constraint. Nothing redundant and nothing padded.

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?

The output schema and annotations cover the return shape and safety profile, so those gaps are acceptable. But for a 7-parameter mutation tool with 0% schema description coverage, leaving the meaning/valid range of the required success_score and the role of request_id undocumented is a material omission.

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 carry the load, and it does explain the optional actual_cost_usd / actual_latency_ms / actual_energy_wh semantics and the null-means-unknown rule. It leaves decision_id, request_id, notes and especially the scale/range of success_score entirely unexplained.

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?

Names a specific verb and resource ('attach one observed outcome to a Wu Wei decision'), which is clearly distinct from siblings like route_task and submit_evaluation. It doesn't explicitly name the sibling that produces the decision_id (presumably route_task), so the pairing is inferable rather than stated.

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 'one append-only outcome per decision' constraint implies when the tool applies and when it will refuse, and 'observed outcome' signals post-execution timing. However, it never says where decision_id comes from or what to do instead if an outcome already exists (e.g., no sibling for updating an outcome is named).

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