StartupPerks

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds substantial behavioral context: it checks eligibility criteria (stage, funding gate, raised-amount cap, etc.), ranks categories by user needs, excludes paused/closed programs, and clarifies that values are 'headline maximums, not guarantees.' This goes well beyond the annotation baseline.

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 dense but every sentence carries information: purpose, usage, behavioral specifics, return format, and caveats. It is front-loaded with the core purpose, then proceeds logically. For a tool with 12 parameters and complex ranking logic, this length is justified and well-structured.

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 fully accounts for the return value: up to 25 programs, each with value, qualification status and reason, how to claim, links, and a realistic total. It also covers exclusions (paused/closed) and the ranking logic. Nothing an agent needs to call it correctly is missing.

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 the baseline is 3. The description adds meaningful context on the 'needs' parameter (ranks the categories the user needs first and takes each need in turn) and clarifies the 'limit' behavior via the max-25 return. It doesn't add detail for every parameter, but the marginal value is clear, earning a 4.

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 verb (rank) and resource (startup perks a company can claim), enumerates providers, and explicitly differentiates from siblings by noting search_startup_perks is for lookup without a profile and get_startup_perk for one program's terms. This is a textbook example of purpose clarity.

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 explicitly states when to use this tool ('when the user describes their own startup and asks what they can get or qualify for') and names the alternatives with their distinct use cases. No ambiguity remains about which tool fits which scenario.

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, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it returns an error when nothing matches, lists the full set of returned fields (eligibility gates, expiry, how to claim, application status, last verified, links, alternatives, category guide), and explicitly states it is read-only. This goes beyond the annotations by detailing the response contents and error behavior.

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 dense paragraph that front-loads the core purpose and usage, then lists the return contents. It is somewhat long but every sentence earns its place by covering usage, return fields, error behavior, and read-only status. The structure could be improved with bullet points or shorter sentences, but it is not bloated.

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 lookup tool with 2 optional parameters, 100% schema coverage, and no output schema, the description is complete. It explains how to invoke it, what it returns in detail, what happens on error, and how it relates to sibling tools. An agent has everything needed to select and call it correctly.

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 the schema already documents both parameters (name and slug) with examples. The description adds context on how the parameters relate to the other tools (slug comes from details_url) and when to use name vs slug, which is helpful but not a major addition beyond the 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?

The description clearly states the tool returns the full terms of one startup program, with a specific verb ('Return') and resource ('full terms of one startup program'). It distinguishes itself from siblings by explicitly mentioning find_startup_perks and search_startup_perks and how to use them together.

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 explicitly says when to use this tool: after find_startup_perks or search_startup_perks by passing the slug, or with a program/provider name when the user asks about one program. It also provides an example and notes that an error should trigger search_startup_perks, giving clear routing guidance.

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 annotations, the description reveals meaningful behavior: exact-name matching for providers/programs, topic expansion via category and rare-word weighting, exclusion of paused/closed applications, and a return summary including 'stated value, the primary eligibility gate and links, plus a page to browse more.' This adds substantial context that the readOnly and idempotent annotations do not 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 dense but every sentence earns its place: purpose and examples first, followed by the sibling distinction, matching behavior, exclusions, return details, and safety. It is front-loaded with the primary verb and resource, and the length is justified by the tool's breadth.

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?

Despite having no output schema, the description tells the agent what to expect in the result set. Combined with the fully documented input schema and annotations covering read-only and idempotent behavior, an agent has enough information to select and invoke this tool correctly across its six optional parameters.

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%, so the baseline is strong. The description adds meaning beyond the schema by explaining how query semantics work ('A provider or program name returns only programs that carry that name; a topic ... also matches the category that covers it') and by clarifying the intent of open_to_any_startup ('programs open to any startup without investor or accelerator backing').

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: 'Search the catalog of 1,000+ startup programs by provider, program or topic.' It gives concrete example queries and explicitly distinguishes this tool from find_startup_perks, so an agent can tell them apart without opening either 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?

It states when to use this tool ('Use it for questions like...') and when not to ('use find_startup_perks instead when the user wants what a specific company qualifies for'). It also lists the browsing modes: category, benefit type, and open-to-any-startup programs, leaving no ambiguity about the selection criteria.

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