Pass-through tax rules

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

Annotations already establish that this is a safe, read-only, idempotent, closed-world lookup, so the bar is lower. The description still adds real behavioral context beyond them: unverified fields come back as null and unsupported state/year combinations return not_covered, which tells the agent how to interpret empty results.

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, front-loaded with the core purpose and followed by the null/not_covered behavior. Every clause carries information; nothing is redundant with the title.

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 output schema, the description correctly takes on the job of describing returned content: conformity status, conformity date, and the plain-language add-back/subtraction. It stops short of describing the actual response shape or how add-back vs subtraction is represented, a minor gap for a two-parameter lookup.

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 both parameters are already documented in the schema, including the DC/NYC notes and the note that files are tax-year specific. The description adds no further parameter detail, so the baseline 3 applies.

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?

Names the specific resource (IRC 168(k) bonus depreciation and IRC 179 conformity) and enumerates exactly what is returned: conformity flag, IRC conformity date, and the add-back/subtraction. It is clearly distinct from siblings like salt_cap or ptet_rules, though it never explicitly contrasts itself with them.

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?

Usage is implied by the resource (check state-level bonus depreciation treatment for a state/year), and the edge-case note 'Unknown states and years are not_covered' hints at valid input boundaries. However, there is no explicit when-to-use guidance or routing to alternatives like coverage or ptet_rules.

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 already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful semantics beyond that: elective_ptet_2026 counts only 2026 files with an elective PTET, and no_elective_ptet_2026 / not_effective_2026 are explicitly not PTET states, preventing a likely misinterpretation of returned categories.

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 tight sentences, front-loaded with what the tool lists, then the field semantics that require clarification. Every sentence conveys information; nothing is padding.

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?

No output schema and no params, yet the description names the key coverage categories and disambiguates the easily-confused ones, which is the essential context for interpreting the result. Minor gap: the full shape of the returned list isn't described, but for a simple enumeration tool this is close to sufficient.

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?

Zero parameters, so a baseline of 4 applies per the rubric. There is nothing to document and the description does not waste space on parameter explanation.

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 and resource ('List jurisdictions and tax years in this dataset') plus explicit field-level semantics for the coverage categories. It doesn't name or differentiate against the siblings (ptet_rules, salt_cap, bonus_conformity), so an agent can infer the purpose but not the boundary vs those tools.

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?

No indication of when to call this versus the sibling tools, or what the typical workflow (e.g. discover coverage before drilling into ptet_rules) looks like. The second half explains what fields mean rather than when to use the tool.

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 already declare a safe, read-only, idempotent, closed-world read, so the bar is lower; the description still contributes real behavior: the not_covered sentinel for uncovered state/year combinations, the fact that files are tax-year specific, and an 'informational, not tax advice' disclaimer. It stops short of describing output shape or per-year coverage boundaries, which matters since no output schema exists.

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 scope and covered subtopics lead, followed by the not_covered return behavior and the disclaimer — sensible front-loading with no filler sentences. The subtopic list is dense but each item tells the agent what it will get back, so it earns its length.

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 two-parameter, fully described, read-only lookup with no output schema, the description covers scope, the topics returned, the negative-result case, and the advice disclaimer. The only remaining gap is any statement of how coverage varies by year or what to do when not_covered is returned (adjacent sibling to try).

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%, so the schema already documents both parameters including the postal-code/DC/NYC conventions. The description only restates the 'one state and tax year' scoping without adding syntax or format meaning beyond the schema, so baseline 3 applies.

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?

Names the resource precisely (elective pass-through entity tax) and the two scoping dimensions (one state, one tax year), then enumerates the subtopics covered: eligibility, election mechanics, deadline, rate, owner credit/exclusion, estimates, sunset. That enumeration makes it distinguishable in practice from generic siblings like coverage or salt_cap, though it never explicitly contrasts itself with them.

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?

There is no statement of when to use this tool versus the sibling tools (coverage, salt_cap, bonus_conformity), and no preconditions or exclusions. The only routing hint is 'Returns not_covered when this server has no file', which describes a response case rather than usage guidance.

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 already cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful context beyond annotations: it returns the cap and steps rather than the deduction, marks pre-2018 years as not_covered, and clarifies that MAGI is used in computation but not written to the usage log.

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 front-loaded with the core computation purpose and then layers in only essential clarifications about output, unsupported years, and logging. Every sentence earns its place with no redundant restatement of schema or annotations.

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 three-parameter computation tool with rich schema descriptions and read-only annotations, the description is largely complete. It states what is returned and clarifies the non-deduction output and unsupported years, though it could say more about output format or error behavior.

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 baseline is 3. The description adds value by clarifying that pre-2018 tax years are not_covered, extending the schema's note on year behavior, and by explaining that MAGI is used for computation but not logged.

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 and resource: compute the federal SALT deduction cap, citing the governing statute and required inputs. It is clearly distinct from sibling tools like bonus_conformity and ptet_rules, but it does not explicitly name or differentiate against those 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 implies when to use the tool by specifying the required inputs and noting that years before 2018 are not_covered. However, it does not explicitly state when to choose this tool over siblings or provide broader usage context beyond the unsupported-year exclusion.

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