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

Well beyond annotations: the credit cost model (1 credit, 2 when >3 ZHomes calls), the ANY-match semantics for events, and the crucial distinction between direct events (work on first search) and change events (need a prior baseline search of the same area) that would otherwise produce silently empty results. Annotations cover the safety profile; the description covers economics and statefulness.

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?

Front-loaded with purpose and cost, then examples, then the event taxonomy. It is long, but with 53 parameters and 29 event enum values most sections earn their place; the grouped event lists and the direct-vs-change note are load-bearing rather than filler.

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?

Given 53 optional parameters, no output schema, and existing annotations, this is close to complete: it covers cost, precedence, event timing pitfalls, and the natural next steps. Minor gaps remain — output shape is only described as 'cards and a map' with no note on result paging or how the `limit` cap interacts with the map view.

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 100%, so the baseline is 3; the description still adds real meaning by mapping natural-language sentences to concrete parameter values and explaining the event taxonomy (direct vs change, baseline behavior) that the bare enum cannot convey. It does not, however, document most of the 53 individual filters' semantics or defaults (e.g. ownership, equity, lot size), leaving those to the schema.

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?

A specific verb plus resource plus data source: 'Search live listings (Zillow data) in Spur with plain English and/or structured filters, including event filters.' It also distinguishes itself from the closest siblings by naming spur_parse_search_query, spur_save_properties, and spur_create_search_automation for their respective roles.

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?

Explicit routing: call spur_parse_search_query first to check interpretation before spending a credit, follow up with spur_save_properties to save liked listings, or spur_create_search_automation for scheduled runs. It also states a clear precedence rule — structured filters win over `query`, and `query` is reserved for qualitative intent that only descriptions can match.

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