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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered; the description adds context that is NOT in annotations: results are 'fast' and 'bounded', every hit carries a DealMachine property ID, and the call spends no credits (a real cost concern on a paid-data API with enrich siblings). Return-shape detail is a bonus given 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?

Four tight sentences, front-loaded with the action and scope. Minor waste: 'Retrieves data without changing records' largely restates readOnlyHint/destructiveHint, though the 'or spending credits' clause earns its place.

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 compensates by stating what each suggestion contains (property ID, optional normalized city/county). Remaining gaps are minor: how state/lat/lng combine with the text query to affect ranking, and what an empty result looks like.

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 says nothing about the query/limit/state/latitude/longitude parameters. The reported 0% coverage reflects the undescribed top-level 'query' wrapper, but the nested fields are in fact documented in the schema (min 2 chars, max 10 suggestions, two-letter state, lat/lng used to rank nearby addresses), so the agent is not blind — just unmapped to the description. Baseline 3.

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?

Specific verb+resource: 'Autocomplete property addresses. Return fast, bounded street-address suggestions from DealMachine property data.' The word 'autocomplete' plus 'partial street address' clearly separates it from full-query siblings like property_search or location_search, though no sibling is named explicitly.

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 'autocomplete' / 'fast, bounded suggestions' (typeahead-style lookup on a partial string), but the description never states when to use this versus dealmachine_property_search, dealmachine_location_search, dealmachine_post_addresses_validate, or the dealmachine_enrich_* endpoints. The agent must infer the routing.

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