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

Annotations declare readOnlyHint=false and destructiveHint=false, but the description adds critical pricing behavior (2 credits unless pulled in last 7 days, then free) and a required user-confirmation step — neither of which is in the annotations. This is exactly the kind of context that structured fields cannot capture.

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-loads the cost model, then the return contents, then the parameter source, then the confirmation requirement, then the alternative. Dense but every sentence contributes. Slightly long, but nothing is wasted.

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?

An output schema exists, so return values need not be explained, and the description correctly focuses on cost, sourcing, and routing. It covers all the decision-relevant information an agent needs before calling. Minor gap: does not mention authentication or rate-limit properties, though the credit model covers the main constraint.

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 coverage is 100% and the schema already documents property_id with an example (prop_123456). The description adds that it starts with 'prop_' and where to source it, which is mildly useful but largely redundant. Baseline 3 applies when the schema does the heavy lifting.

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+resource ('Returns the full record for one property') and enumerates exactly what the record contains (owners, building/lot, value/equity, mortgages, foreclosure filings, last sale). It distinguishes itself from siblings by naming get_nyc_preforeclosure_detail as the alternative for NYC preforeclosures.

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?

Explicitly names where to get the property_id (run_national_property_search or run_active_investor_search), states a confirmation requirement ('Tell the user it costs 2 credits and get their go-ahead before calling'), and routes NYC preforeclosure queries to get_nyc_preforeclosure_detail. Covers when-to-use, prerequisites, and the sibling alternative.

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