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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds billing semantics ('charges nothing') and, importantly, discloses the return payload — reason, per-path score and time, and the ready input for the chosen path — which is needed since no output schema exists.

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?

A single dense sentence, but it is front-loaded with the core action and closes with the two most decision-relevant facts (no execution, no charge). Every clause earns its place, though the parenthetical path list makes it read as a run-on.

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?

With no output schema, the description correctly takes on the burden of describing the return shape (reason, scores, timing, ready input). Combined with 75% parameter documentation and annotations covering the safety profile, an agent has nearly everything needed; only explicit when-to-use routing against the path_* siblings is missing.

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 coverage is 75% with door, meta, objective and dataset_ref all carrying schema-level documentation, so the structured fields do most of the work. The description text adds nothing about parameter semantics (e.g. what 'door' values mean or what dataset_ref null implies beyond the schema note), so the baseline 3 applies.

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 function: deciding which of eight named paths (reuse, rerun, answer, tool_run, estimate, bespoke, ask, none) a data question should take. The listed outcomes map directly onto the sibling tools (path_reuse, path_rerun, etc.), and 'Executes nothing' makes clear this is the router rather than an executor, so an agent can separate it from those siblings.

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?

Usage is only implied: the phrase 'Executes nothing and charges nothing' signals a cheap triage step to run before committing to a path, but the description never says when to call this versus calling path_reuse/path_rerun directly, nor what conditions favour it. Adequate inference, no explicit routing guidance.

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