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

Beyond the annotations (which only say non-read-only, non-idempotent, non-destructive), the description discloses three useful traits: data is keyed to this conversation, personal contact details must not be included, and records auto-expire after 24 hours. It stops short of describing update-vs-create behavior or what a save returns.

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?

Three tight sentences with the action and scope front-loaded, then the PII constraint, then the retention rule. No filler or repetition, though the parenthetical field list is the least load-bearing part.

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 mutation tool with ~30 nested optional fields and no output schema, the description covers retention and the PII prohibition but omits update semantics (partial vs full replacement of criteria, what clear_fields does, when a new preference_set_id is created). Adequate but with visible gaps given the tool's complexity.

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 67% and the nested criteria object already documents most fields with patterns, enums and semantics (e.g. budget_min/max, priorities ordering). The description lists broad categories (location, budget, timing, practice area, language, priorities) but adds essentially no meaning beyond that enumeration. The 'no personal contact details' rule is a genuine constraint on the criteria parameter.

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 pair (save/change) and resource (matching criteria) and enumerates the criterion categories, so the agent knows this persists filtering preferences for a conversation. It does not, however, distinguish itself from close siblings like get_matching_requirements or find_attorneys, which an agent would need help disambiguating.

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?

The description never says when to call this versus get_matching_requirements (read the stored criteria) or find_attorneys (act on them). 'For this conversation' implies scoping but provides no explicit when/when-not guidance or named alternatives among the ten siblings.

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