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

With no annotations, the description carries the full burden and does so: it discloses patch semantics ('Only the fields you send change'), the preview side effect ('changes recorded, no price moves'), what auto announces, that approve pins pricing to the last approved estimate, and the exact auth requirement (Last Price credential with routing write scope, or the key of the agent that registered an unclaimed workspace). That is unusually complete for an unannotated mutation tool.

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?

Front-loaded with the three capabilities before the conditional logic, and every sentence carries operational content rather than filler. It is dense and clause-heavy, which costs some readability, but nothing is truly redundant.

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 3-parameter mutation tool with no annotations and no output schema, the description covers prerequisites, partial-update behavior, preview vs live side effects, and mode reporting. What it omits is how pending approve-mode changes are enumerated (list_learned_price_changes) and a fuller picture of the response, but the essential call-time information is present.

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 baseline is 3; the description goes beyond it by documenting cross-parameter interaction (enabled=true without apply_mode keeps the saved mode or runs preview, enabled=false keeps the saved mode) and by noting that the resulting mode is reported in the answer. It adds real semantics rather than restating field definitions.

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 verb and resource — turning learned pricing on/off, selecting how new estimates are applied, and toggling its email — which is precisely distinguishable from get_learned_pricing (read) and decide_learned_price_change (approve a single change). The final clause names that sibling explicitly, so an agent can route between them without opening any schema.

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?

Explains the conditions well: apply_mode is optional, omitting it keeps the saved mode or falls to preview, auto applies immediately while approve defers each change to decide_learned_price_change, and enabled=false preserves the saved mode. It never states when to prefer reading current settings via get_learned_pricing first, but the mode/alternative guidance is clear and actionable.

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