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

Annotations only give the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds substantial behavior beyond that: asynchronous scheduled monitoring outside the conversation, the alert categories recorded (new listings, price reductions, relistings), replace-on-same-name semantics, the refusal of fair-housing-style people preferences, and the shape of the response (hard/soft/excluded interpretation plus a stored-data preview).

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?

One dense paragraph with the core action front-loaded, then monitoring behavior, replacement semantics, and the return/fair-housing caveats. Every clause carries information, though the alert-preference enumeration is slightly list-like and could be tightened.

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 explains what comes back (criteria interpretation and a preview from stored data). It also covers the policy boundary (fair housing refusals) and the persistence/monitoring model, which are the non-obvious things an agent needs before calling this five-parameter, nested-schema tool.

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 reported at 0%, so the description must compensate, and it does for the semantically tricky parts: alert_prefs (min_score, new listings, price drops with optional minimum percent or amount, back on market) and the hard-vs-soft-vs-excluded criteria distinction. It adds nothing for name, priority, or monitoring, leaving those to the schema's enums and defaults.

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 ('Save the user's search criteria once as a named, persistent watchlist') and explicitly anchors it to a sibling's criteria model ('same criteria as search_properties'). An agent can distinguish this from search_properties and manage_property_watchlist without opening either 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 context clearly: save criteria once, then Realty.Bingo monitors on a schedule independent of any conversation, and re-saving with the same name replaces the prior watchlist. It does not explicitly say when to prefer this over manage_property_watchlist or when not to save, so it stops short of full alternative routing.

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