SavePropTax

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

No annotations are provided, so the description carries the full burden. It discloses the possible statuses, including 'not_enough_data', 'county_not_served', and 'already_filed', which are important behavioral outcomes. It also clarifies that the tool is non-destructive ('never raise it'), which is valuable.

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 single paragraph but is dense and well-structured. It front-loads the core purpose, then lists the return statuses and outcomes efficiently. Minor redundancy (e.g., 'free' repeated) but overall concise.

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 the tool has 2 parameters, no output schema, and no annotations, the description covers the main behavioral aspects: possible statuses, the meaning of a qualifying result, and the safety guarantee. Missing nuance on how to interpret each status, but acceptable for the complexity.

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 explains both parameters (address and unit). The description adds no additional parameter-specific meaning beyond the schema, but since coverage is high, baseline 3 is appropriate.

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 tool's purpose: checking if a California home qualifies for Proposition 8 property tax reduction. It uses a specific verb ('check') and resource ('property tax savings'), and distinguishes itself from siblings by mentioning the continueToken for start_filing.

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 explicitly mentions the tool is free and can only lower taxes, and implies it should be used before start_filing by referencing the continueToken. However, it does not explicitly state when not to use it or name alternatives, though siblings are get_filing_status and start_filing.

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?

With no annotations, the description carries the burden of disclosure. It clearly states the tool returns only a coarse status and explicitly guarantees no personal information, addresses, or amounts, which is valuable privacy/scope context. It does not mention potential errors or authentication, but for a simple read-only status check the disclosure is sufficient.

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 two short sentences, front-loads the purpose, and adds the privacy caveat without unnecessary elaboration. Every phrase 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?

The tool is simple: one required parameter, no output schema, and the description enumerates all possible return statuses, so the agent can interpret results. It lacks explicit error/edge-case handling, but the 'unknown' status and clear docId dependency make it sufficiently complete.

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 schema already fully describes the single docId parameter and its provenance from start_filing, so description-level parameter detail is not critical. The description adds no format or syntax details beyond the schema, which is acceptable given 100% schema 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 uses a specific verb ('get') with a clear resource ('coarse status of a filing') and identifies the lookup key ('by document id'). It enumerates possible status values, making the tool's purpose unambiguous and distinct from siblings like start_filing and check_property_tax_savings.

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 implies this is used after a filing has been started, since it queries status by document id and the schema notes docId comes from start_filing. However, it does not explicitly state when to use this tool versus alternatives or any exclusions/conditions.

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?

With no annotations, the description carries the full burden of disclosure. It reveals that the tool emails a signing link to the owner's email, never returns the link, and that the owner must review, sign, and pay $29 before filing. It also discloses the 24-hour token validity, providing important operational context beyond the schema.

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?

Three concise sentences, each adding essential information: the main purpose, the workflow and non-return of the link, and the token requirement. No redundancy or filler, and the most critical action is front-loaded.

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 no output schema and no annotations, this description is remarkably complete. It covers the prerequisite (qualifying check), the token validity, the owner's role and fee, and the fact that the link is not returned. The only missing piece is explicit error handling, but the prerequisite conditions imply failure modes, making this sufficient for correct invocation.

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%, but the description adds extra meaning: it clarifies that ownerEmail receives the signing link, and that continueToken is tied to a qualifying check and valid for 24 hours. This goes beyond the schema's parameter descriptions, which only state origin, not the validity window or email role.

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 ('Start a county filing') and the specific prerequisite ('for a property that qualified in check_property_tax_savings'). It also distinguishes this from siblings by referencing the prior check tool and implying this is the initiation step, unlike get_filing_status which would monitor progress.

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 explicitly ties usage to a prior qualifying step: 'Requires the continueToken from a qualifying check (valid 24 hours).' This implies the tool is used after check_property_tax_savings and provides a time constraint. It does not explicitly compare to get_filing_status, but the purpose is clear enough for an agent to select it correctly.

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