company-technographics

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

Annotations already indicate read-only and idempotent behavior. The description adds valuable context about the output contents (firmographics, hiring stats, tech stack adoption context), aligning with the annotations. No contradictions.

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?

Single sentence with no filler. Action is front-loaded ('Resolve a company domain'), includes a concrete example, and lists output categories concisely. Every word serves a purpose.

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 simplicity (one parameter, read-only, idempotent) and the descriptive content covering input and output categories, the description is complete. No output schema is needed as the list of return categories suffices.

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% for the single parameter 'domain'. The description adds clarity with an example ('walgreens.com') and explains that the domain is resolved to a full profile, which enhances meaning beyond the schema description.

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 uses specific verbs ('Resolve a company domain') and clearly distinguishes from siblings: it returns a full profile (firmographics, hiring stats, tech stack) while siblings focus on technology lists or searches. No ambiguity.

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 when a domain is known, but lacks explicit when-not-to-use or alternatives. Sibling tools are mentioned in context signals but not in the description, so guidance is only implicit.

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 indicate readOnly and idempotent behavior. The description adds transparency about sorting behavior and output structure (company counts), which goes beyond annotations.

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 extremely concise with no extraneous words. It gets straight to the point and fits in a single sentence.

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?

While the description covers the core purpose and sorting, it omits pagination behavior and does not fully describe the output format. Given the schema provides parameter details, some gaps remain.

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 description explains the 'sort' parameter's enum values but does not cover 'page' or 'page_size'. With 0% schema description coverage, partial compensation is provided.

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 tool lists all technologies in the dataset and provides per-technology company counts. It distinguishes itself from sibling tools that focus on companies rather than technologies.

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 for browsing technologies but does not explicitly state when to use this tool versus alternatives. No exclusions or when-not guidance are provided.

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 and idempotentHint. The description adds that results are ranked by usage, names are case-insensitive, and match modes determine filtering logic. This goes beyond annotations by explaining sorting and search behavior without contradiction.

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 two sentences: the first clearly states the core purpose with ranking, the second provides essential usage notes. Every sentence adds value, no fluff. Front-loaded with the primary function.

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 tool has no output schema, but as a search tool, the description adequately covers input semantics and behavioral notes (case, match modes, exploration with list_technologies). It lacks details about output format or pagination, but given the context signals and the straightforward nature of the tool, it is sufficiently 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 coverage is only 25% (only technologies parameter has a description). The description compensates by explaining case-insensitivity for technologies, the two match modes, and that list_technologies can discover available technologies. This adds meaning beyond the schema's enum definitions and defaults for page, page_size, and match.

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 verb 'Find' and the resource 'companies by technologies', and mentions ranking by usage. It distinguishes from sibling tools: get_company_by_domain retrieves a single company, list_technologies lists available technologies. A specific verb+resource with differentiation.

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 explains case-insensitivity, the scope of technologies tracked (10,000+), and suggests using list_technologies to explore. It also clarifies match modes: 'any' requires at least one technology, 'all' requires every one. This provides clear context for when and how to use the tool, though it does not explicitly state when not to use it.

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