The AI Agent Index

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and determinism profile needs no restating. The description adds only that the response is 'full structured details', which is a mild hint about return richness already covered by the output schema. No notice of what happens if the slug is unknown.

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 sentence, front-loaded with verb and resource, with the lookup key placed at the end. No padding or redundant clauses.

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 a rich output schema, complete annotations, and a fully documented parameter, the description covers enough for correct invocation. A small gap remains around behavior for a missing/invalid slug and the recommended path from search_agencies to this tool.

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% and the single parameter already includes an example ('taycon-ai'). The description merely repeats that the slug is the identifier; per the baseline rule, 3 applies when the schema fully documents the parameter.

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 ('Get') and resource ('full structured details for a specific AI automation agency'), and names the lookup key (slug). It is distinguishable from search_agencies/list_categories by being a single-record fetch, though it never explicitly contrasts 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 only implied: 'by its slug identifier' signals a direct lookup once a slug is known, and the presence of search_agencies as a sibling hints at a discovery-then-fetch flow. No explicit when-to-use or when-not-to-use guidance (e.g. use search_agencies first to find the slug) is given.

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, so the safety profile is covered; the description adds genuinely new behavior — that competitor price references and GitHub star counts are resolved to live values before returning, which tells the agent the numbers are fresh rather than cached. It does not state error behavior for an unknown slug, but that is a minor gap against otherwise strong coverage.

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 action and lookup key, then the returned payload, then the one non-obvious behavioral note about live resolution. No filler and nothing buried.

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?

An output schema exists, so enumerating return fields is technically bonus rather than necessity, and the description still flags the live-resolution behavior that a schema cannot convey. What remains missing is what happens on an invalid or unknown slug — the one thing an agent needs to handle failure.

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 a single parameter at 100% schema coverage and a concrete example list in the schema, the schema already does the work. The description reinforces the lookup key ('by its slug identifier') but adds no format, casing, or resolution rules beyond that, 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?

States a specific verb+resource+lookup key: 'Get full structured details for a specific AI agent by its slug identifier.' This implicitly contrasts with the search_* siblings (which take query terms, not slugs), but it never names them, so differentiation is inferential rather than explicit.

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 'by its slug identifier' phrasing implies you should already know which agent you want, which is the de facto condition separating it from search_agents. However, there is no explicit when-to-use statement, no mention of falling back to search_agents to obtain a slug, and no exclusions.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without prose. The description adds modest value by naming the two category namespaces being enumerated, but its mention of returned fields (slugs, names, counts) largely duplicates the output schema, so it doesn't contribute much behavioral context beyond structured data.

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, zero waste, with the resource and its scope front-loaded and the return fields following. Every clause carries information an agent can act on.

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 a full output schema, rich annotations, and no parameters, the description needs only to establish scope and it does. The one missing piece is how the returned slugs connect to the sibling search tools, which would make this a complete discovery-to-filter story.

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 tool takes zero parameters, which is the baseline-4 case; there is no argument semantics to explain. The description correctly implies an unfiltered enumeration of everything in the index, which matches the empty input schema.

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 ('List') and resource ('available categories') with explicit scope: it covers both the AI agent software categories and the AI Automation Agencies services directory. That dual-domain scope plus the enumerated return fields makes it unmistakable against siblings like search_agents or get_agency, which operate on individual entities rather than the taxonomy.

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 never says when to call this versus the search/get siblings, but the implied usage is fairly clear from context: it is a taxonomy/discovery call that would precede filtered searches. Nothing is explicit about prerequisites or about feeding the returned slugs into search_agents or search_agencies, so guidance remains inferential 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?

The annotations already declare readOnlyHint, idempotentHint, destructiveHint, and openWorldHint, so the safety profile is covered. The description adds useful domain scope and entity definition, but it does not describe matching behavior, result ordering, or other behavioral traits beyond what the structured fields provide.

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 a single compact sentence with a useful parenthetical definition, and the core purpose is front-loaded. Every part earns its place.

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 an output schema present, read-only annotations, and complete parameter descriptions, the description is sufficient for an agent to invoke the tool correctly. The main gap is that it does not help the agent choose between this and sibling tools like search_agents or get_agency.

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 all six parameters are already documented in the schema. The description echoes four key filter dimensions but adds no syntax, enum, or default details beyond the schema, making the baseline 3 appropriate.

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 clear verb and resource: search the AI Agent Index for AI automation agencies, and it defines the entity as services firms that build AI solutions for clients. It does not explicitly distinguish this tool from sibling tools such as search_agents or get_agency, which keeps it from 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 description implies usage by saying the tool can filter by service type, industry, tools, or region. However, it gives no explicit guidance on when to use this versus search_agents or get_agency, and no when-not conditions.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only that results are 'structured agent data' and hints at filter semantics; it does not mention result caps, pagination, or empty-result behavior beyond what the schema's limit field already says.

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 core action, then the return value, then the filter usage. The 'Returns structured agent data' sentence is mildly redundant given an output schema exists, but it still sets expectations quickly.

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 an eight-parameter, zero-required search tool with a full output schema and rich annotations, the description covers the filter surface and the search-vs-fetch distinction adequately. Only marginal gaps remain (no-result behavior, result cap of 20, no pointer to get_agent for detail 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 all eight parameters (including the nuanced agent_type examples and mcp role values) are already documented in the schema. The description only restates the filter list and one mcp=server example, adding essentially no syntax or format detail beyond structured data – 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?

States a specific verb and resource ('Search the AI Agent Index for agents') plus the return shape ('structured agent data'), and implicitly separates itself from the singular get_agent / get_agency siblings by framing it as criteria-based search. An agent can tell it apart from its siblings without opening a schema.

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 clear context for use by enumerating the filter dimensions (category, sub-type, pricing, integration, capability, MCP role) and even clarifies the mcp=server semantics. It stops short of naming the alternative route (use get_agent once you know the ID) or stating when not to search, so no explicit exclusion.

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