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

Beyond the annotation readOnlyHint=true, the description adds useful behavioral details: it returns only 'active' listings and defaults to the most recently updated when no filters are provided. This gives the agent a clearer picture of what to expect, though it omits details like pagination or result format, which are not covered by annotations.

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 two sentences, front-loaded with the main purpose and a concise note on default behavior. Every sentence provides value and there is no redundancy or fluff.

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 tool with 13 parameters, no output schema, and no sibling-based guidance, the description is too sparse. It does not explain what fields a returned listing contains, how results are sorted beyond 'recently updated', whether pagination is supported, or what 'active' means. The openWorldHint and readOnlyHint are given, but the description still leaves many operational details unexplained.

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 tool description adds no parameter-specific meaning, and the schema only documents descriptions for about 54% of the 13 parameters. Unannotated parameters like sort, limit, min_price, max_price, listing_type, and property_type lack explanations, and the description does not compensate. This leaves the agent guessing on a significant subset of inputs.

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 clearly states the tool searches active Trellistate property listings, with a specific verb and resource. While it doesn't explicitly distinguish from siblings like get_listing or list_recent, the 'Search' verb and the filter-optional behavior indicate its role as a search tool, though it may overlap with list_recent's recent-listings functionality.

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 provides implied usage context: 'All filters are optional; with no filters it returns the most recently updated listings' suggests it can be used both for filtered searches and for retrieving recent listings. However, it does not explicitly state when to prefer this over list_recent or get_listing, nor does it mention any exclusions or alternatives.

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