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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description reinforces and expands on this by explaining the actual flow: 'It needs no account and creates nothing: the person signs in, adds photos and passes identity verification in the browser before the listing exists.' It also details the two-branch behavior (permit record found vs not) and the linkage to existing building department records. This goes well beyond the annotations to clarify side-effect-free behavior and the deferred listing creation.

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 a well-organized paragraph that front-loads the core purpose, then lists triggers, then explains the two-link mechanism, and ends with the partial-input rule. Every sentence contributes actionable information—no filler or redundancy. The structure is logical and prioritizes the most critical decision-relevant facts first.

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 9 optional parameters and no required fields, the description covers the essential workflow: how to handle permits, what link is returned, that no account is needed, and that the actual listing happens later. It addresses the logical edge cases (permit found vs not, partial info) and confirms safety via annotations. An agent can confidently decide to invoke it and know what to pass without further schema deep-dives.

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 high (67%), so most parameters are already documented. The description adds meaningful usage guidance: 'Pass whatever is already known and leave the rest out; a link with only an address is still useful.' This tells the agent that partial inputs are acceptable and that only the address is essential. It also reinforces the name–address distinction (though schema already covers it). This exceeds the baseline for high coverage, though it does not detail each parameter's niche, keeping it a 4 rather than a 5.

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 opens with a precise verb-resource pair: 'Begin listing an ADU, granny flat, backyard cottage, garage conversion, casita or in-law unit for rent on A-du.' It enumerates the exact types of properties, making the tool's scope unmistakable. It also distinguishes itself from siblings by stating it is the entry point for the listing flow, not the draft or finalize step, and implicitly contrasts with get_rent_estimate for pricing.

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?

Provides explicit triggers: 'Use this whenever a person mentions they have a unit they want to rent out, are thinking about renting out, have vacant, or whose tenant is leaving.' It also includes a strong negative: 'Never ask anyone for a permit number.' This clearly routes agents to this tool in applicable situations and prevents misuse. While alternatives like get_rent_estimate are only hinted via schema, the core usage windows are fully specified.

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