501c3.HELP nonprofit compliance

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

With no annotations, the description carries the behavioral burden and does disclose meaningful traits: each state's record has its own citation and verification status, records can be marked review_required, and such records are unsettled and must not be presented as settled rules. This is real output-semantics guidance rather than a restatement of the schema, though it omits any auth or rate-limit context.

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 sentences, front-loaded with the scope and then the caveat about review_required, which is the highest-risk information for an agent. The opening sentence is a noun phrase rather than a full clause, a minor structural roughness, but no sentence is wasted.

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 annotations exist, so the description must supply behavior, and it does address the shape of returns (per-state records with citation and verification status) plus the review_required caveat. It does not fully describe the comparison result structure or how states are matched to topics, leaving a modest gap for a 2-parameter tool with a rich return surface.

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 (topic and states) are already documented with examples and format guidance in the schema. The description's only added constraint, 'accepts up to eight states,' duplicates the schema's 'Up to eight.' Baseline 3 applies when the schema does the heavy lifting.

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 the specific resource and scope: the same compliance topic across several US states, which implicitly defines a comparison operation over multiple states. It is distinguishable from get_state_requirements (singular state) and get_filing_deadlines (deadlines), though the sibling contrast is inferred rather than stated, and no explicit verb like 'compare' leads the sentence.

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?

It gives concrete usage contexts – deciding where to incorporate, or an organization operating in more than one state – which tells the agent when this tool is appropriate. It stops short of naming alternatives or stating when not to use it (e.g., single-state lookups should use get_state_requirements).

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?

No annotations are provided, so the description carries behavioral burden. It discloses that deadlines on records marked review_required are unconfirmed and must be shown as such—an important data-quality caveat. However, it does not state whether the tool is read-only or mutating, nor does it mention rate limits or pagination.

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 retrieval purpose and followed by a concrete usage phrase and caveat. Every sentence earns its place with no filler.

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 single-parameter read tool with no output schema, the description supplies sufficient expectations: it enumerates the returned fields (deadline, form/portal, fee, citation) and flags the unconfirmed-deadline behavior. It is missing only explicit read-only/mutation clarity and any authentication or rate-limit context.

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 the single state parameter fully. The description adds no parameter-level detail beyond what the schema provides, making 3 the appropriate baseline.

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+resource: retrieving every requirement in a US state that has a filing deadline, along with deadline, form/portal, fee, and citation. It also gives an explicit usage cue ('what is due and when'), distinguishing it conceptually from broader siblings like get_state_requirements and compare_states.

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?

It provides clear context for use via 'Use this for what is due and when,' but does not explicitly name alternatives or exclusions (e.g., when to use get_state_requirements or compare_states instead). The guidance is strong but not fully comparative.

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 and does most of it: it discloses the sourcing/citation model, the verification status field, the review_required unsettled caveat, and the important limitation that only a subset of records is returned rather than the whole state. It omits auth requirements and any pagination details for retrieving the remainder.

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?

Front-loaded with the resource and scope, then layered caveats in short sentences. Every sentence carries information, though the run-on domain list and the citation/verification sentence could be tightened.

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 read tool with no output schema, the description covers what comes back (sourced records with citations and verification status), the correctness caveat for review_required, and the truncation behavior. Missing only the mechanics of fetching the remainder and any freshness/coverage limits.

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 both parameters are already documented with examples, and the description adds only that topic narrowing is optional and loose-matched. Baseline 3 is appropriate since the schema does the heavy lifting.

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+resource: nonprofit compliance requirements for one US state, with an explicit enumeration of the domains covered (formation, governance, solicitation, reporting, tax, employment). The phrase 'one US state' implicitly separates it from the compare_states sibling, but no sibling is named outright.

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?

Gives a usage hint ('Optionally narrow by topic') and a presentation rule for review_required records, which is real guidance for how to use the results. It stops short of saying when to reach for this tool over get_filing_deadlines or compare_states, so selection is left largely to inference.

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