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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower, and the description adds real semantics: 'save (also tracks it)' and 'dismiss (never shown again)' explain durable side effects. It also discloses the return payload ('learned preference suggestions and clarifying questions'), which matters because there is no output schema.

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 verb and the discriminating enum values, then the guardrail, then the return note — three sentences, no filler. The inline enum parentheticals are dense but each one adds usable meaning rather than restating the schema.

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 four-parameter write tool with no output schema, the description covers the feedback semantics and return values but leaves the identifier parameters and the reasons cap unexplained. An agent still cannot determine from the description alone which id to supply or whether one is mandatory.

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 carries the burden: it enumerates all seven feedback values and all ten reasons with meaning, matching the schema enums. However, the listing_id/property_id parameters (and their rrl_/rrp_ patterns), the maxItems=5 cap on reasons, and which identifier is required are never addressed.

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 ('Record') plus resource ('the user's reaction to a property') and enumerates the exact feedback vocabulary, so the agent knows precisely what payload is accepted. It is clearly distinguishable from watchlist/alerts siblings by being about reaction capture rather than watch management.

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?

"Only when the user says so" is an explicit when-to-use constraint that prevents proactive/unsolicited logging. It does not name alternatives (e.g., track_property or manage_property_watchlist) or describe the inverse case, so it stops short of full routing guidance.

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