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

The description adds meaningful context beyond annotations: automatic deletion after 24 hours, a prohibition on personal contact details, and a clear statement that this is a listing service with no paid placement. It does not explain merge-vs-replace semantics for updating criteria, what destructive behavior is implied by destructiveHint=true, or how clear_fields interacts with saving.

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?

The description is four short sentences, front-loaded with the core action, and every sentence carries relevant information about scope, privacy, retention, or service model. It is efficient, though the trust-related disclaimers could be slightly compressed.

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 complex tool with a large nested criteria object and output schema, the description covers purpose, privacy constraints, and service-model context well. It is incomplete on update semantics — whether fields merge or replace, how clear_fields works, and how to read existing criteria — which matter for correct invocation.

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?

The description summarizes the kinds of criteria that can be set (location, budget, timing, practice area, language, sort priorities), which helps orient the agent. But it does not mention clear_fields or preference_set_id semantics, and with only 67% schema coverage those undocumented parameters rely on the schema alone.

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?

The description states a specific verb (save/change), resource (search filters), and scope (this conversation), and enumerates the filter categories covered. It does not explicitly distinguish itself from siblings like get_search_filters or update_matching_preferences, so an agent must infer the boundary.

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 implied by 'Save or change search filters ... for this conversation,' which tells the agent to call it when criteria need to be set or modified. However, there is no explicit when-not guidance, no mention of reading filters via get_search_filters, and no explanation of how it differs from update_matching_preferences.

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