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

With no annotations, the description carries the full behavioral burden, yet it says nothing about data freshness, whether records are live or cached, rate limits, required entitlements, or failure behavior when a county lacks a 311 feed. It does disclose the substantive behavior (data aggregation plus deduction calculation plus document generation), which is worth some credit, but the operational profile is silent.

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?

A single front-loaded sentence with the action and the outcome stated up front; the statutory citations are dense but they carry real meaning for an agent deciding relevance. No filler or restatement of the name.

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 6-parameter, no-output-schema tool with no annotations, the description covers what is computed and what artifact is produced (Exhibit B-1 as json or html via the schema) but omits jurisdiction coverage limits and the shape of returned deduction data. Adequate to decide relevance, thin for confident execution.

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 schema already documents parcel_id, address, jurisdiction, county, market_value, and the json/html format switch. The description adds only indirect signal — 'calculate statutory obsolescence deductions' hints that market_value feeds the math — without naming or clarifying any 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 plus resource ('Audit a parcel') and enumerates the exact data sources it consults (municipal code enforcement, 311 blight databases, unfit dwellings, demolition orders, exterior violations). It also names the concrete deliverable (Exhibit B-1 with statutory obsolescence deductions), distinguishing it from adjacent siblings like audit_municipal_permits or get_condition_evidence_catalog.

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 blight/code-enforcement focus implies when to reach for it, but there is no explicit when-to-use/when-not-to-use guidance and no mention of alternatives among the many audit_* siblings. An agent must infer selection from the legal citations alone.

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