PE or Not?

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds substantive behavior on top: differing coverage per industry (dental/eye cover all NPI-registered practices; vet/derm/GI only tracked groups), the caveat that some listings come from individual NPI records and may not be confirmed open, and the exact response shape including counts, total, paging and coverage note.

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-loads the verb, resource and scope in the first clause, then examples, then label glossary, then return/coverage notes. The long parenthetical label glossary is verbose but each entry carries real semantics, so little is wasted, though it reads as one dense block.

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 8 optional params and no output schema, the description correctly takes on the burden of explaining return contents and data-quality caveats. The one gap is that it never says what happens when no location is supplied, even though zero parameters are required.

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 already 88%, so the baseline is 3, but the description goes beyond the schema by defining every label value, giving the pe/no_pe aliases, and explaining the limit-100/next_offset paging loop. Remaining params (zip, city, state, name) get no extra meaning beyond their schema descriptions.

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?

A specific verb (List) plus concrete resources (dentists, eye care, vets, derm/GI practices) and the geography scope, with worked example queries. It implicitly separates itself from lookup_business/get_group by being an area search, but never names the siblings, so the differentiation is left to inference.

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?

Concrete trigger examples ('dentists in Plano, TX with no PE ties', 'PE-backed eye doctors in 75024') show exactly which user requests should route here. No explicit when-not guidance or named alternatives, which keeps it short of a 5.

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 behavior, so the safety profile is covered. The description adds substantive value beyond that by disclosing the full response shape (stake size, ownership structure type, sources with headline and date, locations by state) and by noting brand-name inputs work. It does not say what happens when the group is unknown or ambiguous, which keeps it from a 5.

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 verb and resource, then a single dense enumeration of returned fields followed by illustrative queries. Every clause carries information, though the field list is long enough that it reads more as an inventory than a structured summary.

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 must carry the return-value burden, and it does so thoroughly by naming each returned attribute. Combined with the example queries, an agent has enough to call it correctly; the only gap is the lack of guidance on supplying id versus name given that no parameter is required.

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%, with each of id, name, and industry already documented including the enum values, so the baseline is 3. The description adds only the parenthetical "(brand names work)", which slightly extends what the name parameter accepts but does not explain the id-vs-name selection or that at least one identifier is required despite zero required parameters.

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 opens with a specific verb and resource ("Get an owner group's ownership details") and then enumerates exactly what that entails: backers, PE stake, holding structure, parent/brands, sources, locations. An agent can tell this is an ownership/provenance lookup rather than a generic business lookup, but it never names or contrasts with the sibling tools find_businesses or lookup_business, so it falls short of a 5.

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 context is concrete: the description gives example questions ("who owns Heartland Dental?", "is Aspen Dental private equity?") and notes that brand names work, which tells an agent exactly what class of query routes here. It offers no explicit exclusions or guidance on when to prefer lookup_business/find_businesses instead, so it is clear context without alternatives.

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 readOnly, idempotent, non-destructive and closed-world behavior, so the description's added value is the outcome taxonomy (match, multiple_matches, possible_matches, no_match, need_location) and the existence of a correction link and coverage signal. That tells the agent how to handle ambiguous or empty results, which annotations cannot. It still doesn't say anything about rate limits or latency.

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, both front-loaded: identification criteria first, then the return payload. The dense enumeration of return fields is efficient rather than padded, and no sentence restates the tool name 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?

With no output schema, the description must carry the return shape, and it does by naming the status values, the 'say' sentence, and per-match fields including confidence and sources. Adequate for a 7-param lookup, though it doesn't specify what happens when need_location is returned or how to recover from it.

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 86%, so the baseline is 3; the description earns above that by ranking parameters implicitly ('a street address or phone number makes the match surer') and by noting city/state or ZIP as the location basis. The note that industry can be inferred from the name is already in the schema, so it adds little there.

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?

Specific verb and resource: 'Checks whether one specific dentist, eye doctor, vet, dermatology or GI practice is private-equity backed'. The word 'one specific' plus the enumerated industries distinguishes it cleanly from find_businesses (multi-result search) and get_group (owner-group lookup).

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 concrete context for use: name plus city/state or ZIP is the minimum, and a street address or phone number makes the match surer, which tells the agent how to gather inputs before calling. It stops short of naming find_businesses or get_group as alternatives or stating when not to use it, so it is clear but lacks explicit routing.

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