Cofounderbase: AI automation agencies

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description contributes the returned field inventory, but says nothing about behavior for an unknown slug (error vs empty), pagination of case studies, or cost of the call — moderate additions over annotations, not rich.

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?

One front-loaded sentence with no filler; the identifier requirement precedes the return-value inventory, and every clause carries information.

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 annotations covering safety and no output schema, the description supplies an adequate field inventory and slug provenance. Missing only edge-case behavior for invalid slugs, which is a minor gap at this 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 0% and the single parameter has no schema-level description, so the description must carry the burden. It does explain the slug's provenance ('from search results'), but gives no format, casing, or example, leaving the agent unsure what a valid slug looks like.

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 ('Full Cofounderbase profile for one agency') plus the identifier ('by slug'), and enumerates the returned fields, which implicitly separates it from the list-oriented siblings search_agencies and top_agencies. It does not name those siblings explicitly, so it stops 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?

The parenthetical '(from search results)' implies the retrieval workflow after search_agencies, which is useful, but there is no explicit statement of when to call this versus search_agencies or top_agencies and no exclusion guidance. Usage is inferable rather than stated.

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?

Beyond the annotations, it discloses that a person reviews every request and that the user receives one confirmation email. That adds meaningful workflow context, though it does not mention timing, rejection handling, or what happens if fewer than 5 agencies respond.

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 short sentences, front-loaded with the purpose and immediately followed by the critical usage constraint and workflow behavior. 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?

The description covers the action, gating condition, human review, and confirmation email, which is useful for a mutation tool with no output schema. However, with 7 parameters and very low schema coverage, it leaves too much parameter meaning unspecified to be fully 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?

Schema description coverage is only 14%, so the description should compensate, but it only clarifies that name and email are user-supplied and that agency_slugs is capped at 5. It says nothing about the required brief or the optional budget, company, and timeline fields, leaving most parameters unexplained.

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 action (request an introduction) and resource (up to 5 agencies via Cofounderbase). It is clearly distinct from the sibling retrieval tools such as search_agencies and get_agency, but it does not explicitly contrast 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?

It gives an explicit gating condition: only call when the user explicitly asks for an introduction and supplies their own name and email. It does not name alternatives or describe when not to use it, but the prerequisite is clear.

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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds value beyond that with the corpus size, the 'evidence-checked' data-quality claim, and the return shape (ranked agencies, a per-match reason, a profile link), which matters given there is no output schema. It omits the result cap implied by limit and any freshness/ranking caveats.

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 with the capability and scope front-loaded, followed by filters and return shape. No filler and no repetition of 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?

For a read-only search tool with no output schema, the description covers the corpus, the filter surface, and the return format including the ranking rationale, which is what an agent needs to plan a call and interpret results. The main omission is the 1-10 limit ceiling and default, which an agent must read from the schema.

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 80%, so per-parameter meaning is largely handled structurally. The description reinforces this by enumerating the filters (country, tool, budget) and supplying concrete values for tool (n8n, Make, Zapier, Retool, Vapi) and currency for budget (USD), but says nothing about limit, leaving one parameter undocumented in both places.

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: searching a named corpus (960+ evidence-checked AI automation agencies on Cofounderbase) by a plain-English need. The exploratory, query-driven nature implicitly distinguishes it from get_agency (single lookup) and top_agencies (presumably a ranked list), though no sibling is named explicitly.

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 framing 'by a plain-English need' plus the list of optional filters implies the intended use case, and the filter list suggests when to narrow results. However, it never says when NOT to use this tool, nor does it route the agent to get_agency, top_agencies, or request_intro.

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 readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that results are ranked by score ("highest-scored"), but says nothing about what a score is, how ties/ordering work, or what the result payload contains.

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?

A single front-loaded sentence with parenthetical examples; every clause carries filter information. It is dense without being padded.

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 3-param, no-required-param tool with no output schema, the definition leaves open the return shape, the default limit (and the 20 cap), and whether filters AND together. Adequate but with clear gaps an agent would have to discover by calling.

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 only 33%, and the description compensates well for `category` by showing that it accepts a use case, a tool name ("n8n"), or an industry, plus the country filter. `limit` remains unexplained in both schema and description, leaving that one gap.

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 a specific resource (agencies) and a specific selection rule (highest-scored on Cofounderbase), with concrete filter examples. It implies ranking rather than keyword search, which separates it from search_agencies, but it never names the sibling explicitly.

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?

"for a use case ..., a tool ... and/or a country" implies the filters can be combined or used alone, which is useful, but there is no explicit when-to-use versus search_agencies or get_agency, and no guidance on what happens when no filters are passed.

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