FairPath Property-Tax Evidence

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

The description discloses side effects beyond the annotations: it 'creates a private audit record' and 'may create or reuse short-lived scoped session and consent records.' It also states boundaries ('does not expose owner, payment, or raw county records') and that it does not 'change an external system,' which is exactly the kind of behavior an agent needs to know.

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 three sentences with no filler. The primary purpose is front-loaded, followed by side effects and then non-goals. Every clause adds useful information.

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 a rich input schema, an output schema, and four required consent-related parameters, the description is complete enough: it states the prerequisite (explicit consent), the side effects, and the data boundaries. There is nothing an agent needs in order to decide whether to invoke it that is missing.

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 80%, so the schema already documents most parameters. The description adds only the 'homeowner-provided' nuance to address and the consent requirement, but does not explain the optional context object or the specific role of consentEvidenceId beyond what the schema states. This is an acceptable baseline given the schema's coverage.

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 action ('Look up a homeowner-provided address and return bounded property context', which clearly differentiates it from the sibling tools explain_evidence_packet and get_county_requirements. It is specific enough for an agent to know what check_property does.

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 names the core trigger ('homeowner-provided address') and an explicit prerequisite ('requires explicit address consent'). It does not explicitly name alternative tools or exclusion conditions, but the context for when to call it is clear.

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

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

Annotations are all 'false', which is low-information, so the description carries the full burden of behavioral disclosure. It does so well: it reveals the side effect of creating a private audit record and scopes what it does not affect (no external system changes, no recommendations or predictions). This adds genuine context beyond the annotations and shows no contradiction with readOnlyHint=false (creating a record is not read-only).

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?

Two sentences with the purpose front-loaded in the first and the boundary conditions in the second. Zero wasted words; every clause earns its place.

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?

With no parameters and an output schema present (which covers return-value details), the description adequately covers purpose and side effects. Nothing an agent needs to invoke this correctly appears missing.

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 has zero parameters, so the baseline of 4 applies. There is nothing for the description to document or compensate for in the schema, and no parameter gap exists.

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 states a specific verb ('Explain') and a specific resource ('evidence categories FairPath can organize into a homeowner-reviewed property-tax evidence packet'). This clearly differentiates it from siblings fairpath_check_property and fairpath_get_county_requirements, which perform different operations on different resources.

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 scope exclusions ('does not recommend a filing position, predict an outcome, or change an external system'), which tell an agent what this tool is not for. However, it never explicitly states when to use it or routes to the sibling tools for the excluded needs, so usage guidance is mostly implied through negative space.

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

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

Annotations declare readOnlyHint=false, which the description usefully nuances: it 'creates a private FairPath audit record but does not... change an external system.' This clarifies the non-read-only side effect and the read-only boundary with respect to external systems — genuinely valuable context beyond what annotations convey. Minor gap: no mention of what happens on invalid countyId, but the output schema and idempotentHint=false cover part of this.

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?

Two tightly written sentences with zero filler. The primary purpose is front-loaded, and the side-effect disclosure follows naturally in the second sentence. Every clause earns its place.

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 an output schema exists and the tool is a single-parameter lookup, the description covers the essential ground: what it returns, the audit side effect, and the non-mutating external behavior. The only notable gap is sibling differentiation (when to choose this over the other FairPath tools), which slightly reduces completeness.

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% — countyId is documented with examples ('harris_tx or collin_tx'). The description adds no parameter-level detail beyond the schema, so the baseline 3 is appropriate since the schema carries the burden.

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 states a specific verb ('Return') and resource ('county property-tax filing guidance and source metadata'), making the tool's function clear. It implicitly distinguishes from siblings (county requirements vs. check property vs. explain evidence packet), though it does not explicitly name the alternatives.

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 no guidance on when to use this tool versus its siblings. It does not state any prerequisites, exclusions, or routing conditions that would help an agent choose between fairpath_get_county_requirements, fairpath_check_property, and fairpath_explain_evidence_packet.

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