IRS 990 Nonprofit Data

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

No annotations provided, so description carries full burden. Discloses data source ('IRS 990 filings') and specific return content ('revenue, expenses, assets, executive compensation, and filing history'). Could explicitly state read-only/safety characteristics, but 'Get' and 'Returns' imply non-destructive read operation.

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 purpose, followed by data scope, then prerequisite workflow. The 'Args:' docstring format is slightly technical but functional. No redundant sentences; each line adds distinct value beyond the structured schema.

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 output schema exists, the description appropriately avoids redundant return value documentation while adequately describing the data domain (IRS 990 contents). Single parameter is fully documented and workflow context with siblings is established.

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?

Input schema has 0% description coverage (only 'title': 'Ein'). Description fully compensates by defining the acronym ('Employer Identification Number') and providing concrete format examples showing both hyphenated and unhyphened forms.

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 specific verb ('Get') and resource ('detailed information about a nonprofit organization by EIN'). The third sentence distinguishes from sibling tool search_nonprofits by establishing the prerequisite workflow (search first, then get details).

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?

Explicitly states 'Use search_nonprofits first to find the EIN,' providing clear prerequisite guidance and delineating this tool's role in the workflow sequence versus the search sibling.

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 the full disclosure burden. It adds valuable behavioral context by noting the return includes 'both filings with parsed data and those without,' alerting the agent to potential data quality variations. However, it omits other behavioral traits like pagination, rate limits, or error handling.

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 efficiently structured with four sentences covering purpose, return value, use case, and parameter definition. The 'Args:' section is slightly informal but clear. No redundant or wasted text.

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's low complexity (1 parameter), presence of an output schema (which handles return value documentation), and 0% schema coverage, the description successfully covers the essential gaps: it explains what the tool does, what it returns (briefly), why to use it, and fully documents the single required parameter.

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?

With 0% schema description coverage (the 'ein' property has no description), the description fully compensates by defining the parameter as 'Employer Identification Number' and providing format examples ('13-1837418' or '131837418'), which is essential for correct invocation.

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 action 'Get' and resource 'filing history'/'IRS 990 filings', clearly distinguishing from sibling tools get_nonprofit_details (general info) and search_nonprofits (search functionality) by specifying the exact document type retrieved.

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 clear usage context 'Useful for tracking financial trends over time', indicating when this tool is valuable. However, it lacks explicit contrast with siblings (e.g., when to use get_nonprofit_details instead) or exclusion criteria.

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 provided, the description carries the full burden and succeeds well: it discloses the data source (ProPublica/IRS 990 filers), specific return fields (name, EIN, revenue, tax status), and pagination behavior (25 results per page, zero-indexed). It misses auth requirements or rate limits, but covers the essential behavioral contract.

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 well-structured and front-loaded with purpose, followed by source, returns, and parameters. While the Args section makes it longer than ideal, this is necessary given the complete lack of schema descriptions, and every line adds value.

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 presence of an output schema (which absolves the description from detailing return structure) and the complexity of 5 parameters with filters, the description is remarkably complete. It covers searchable fields, filters, pagination, and data provenance, leaving only operational details (rate limits) unmentioned.

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 has 0% description coverage, but the description compensates perfectly by documenting all 5 parameters in the Args section with rich semantics: it provides examples for 'query' and 'state', enumerates all NTEE code mappings (1-10), and clarifies the IRS subsection format for 'c_code'.

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 specific action ('Search for nonprofit organizations') and resource (ProPublica Nonprofit Explorer database). It explicitly mentions searching 'by name or keyword,' which clearly distinguishes it from sibling tools 'get_nonprofit_details' and 'get_nonprofit_filings' that imply retrieval by identifier.

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?

While the naming convention (search vs. get) and the description of return fields (basic info vs. likely detailed records in siblings) provide implied guidance on when to use this tool for discovery versus retrieval, there are no explicit statements about when to prefer siblings or prerequisites like 'use this when you don't know the EIN'.

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