Infrabase

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 structurally. The description's 'what it does not change' and 'Read-only' largely restate those annotations rather than adding new behavioral context such as caching, rate limits, or freshness of pricing.

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 no filler. The phrase 'what it does not change' is slightly awkward and ambiguous, keeping it just short of ideal.

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 and no parameters, the description carries the burden of describing the return, and it does list the returned items (price, pages, non-effects). It could be clearer about the shape of 'what it does not change', but the essentials for calling a no-arg read tool are present.

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, so there is nothing for the description to disambiguate and the baseline of 4 applies. No misleading parameter hints are present.

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 names a specific verb ('Returns') and specific resources (price of a featured listing, the pages it appears on, and what it does not change), so an agent can tell it apart from the write-oriented sibling request_featured_listing. It stops short of explicitly naming that sibling, so differentiation is inferred rather than stated.

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?

There is no explicit when-to-use guidance, no prerequisites, and no named alternative. The trailing 'Read-only' hints at the read-vs-write split against request_featured_listing, but the agent must infer that routing decision on its own.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description adds real behavior: the ranking order (same primary job, then secondary job, then remaining categories), the shape of the return (anchor + alternatives + total count), and licensing/attribution obligations (hand-verified, CC-BY-4.0, infrabase_url). Only pagination/truncation behavior is left unstated.

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?

Four sentences, front-loaded with the core action and ranking rule, with no filler. The trailing license/attribution fragments are terse but earn their place by setting an attribution expectation.

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?

There is no output schema, so the description correctly compensates by describing the return payload and ordering. Combined with fully documented parameters and a complete annotation set, only edge behavior (e.g., what happens with an unknown slug or an empty alternative set) 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%, with slug, limit, and eu_only fully documented including format and defaults, so the schema does the heavy lifting. The description adds no parameter-level detail beyond that, making the baseline 3 correct.

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 ("Find alternatives to an AI infrastructure product listed on Infrabase.ai") and immediately distinguishes itself from siblings like get_tool or search_tools by being the alternative-discovery operation. An agent can tell what it returns without opening the 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?

The description implies the workflow (you need an anchor product slug, which the schema notes comes from search_tools), but never states explicitly when to prefer this over get_tool or search_tools, and gives no exclusions. Usage is inferable rather than directed.

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 and non-destructive, so safety is covered. The description adds genuinely useful non-obvious context: data is hand-verified, results are CC-BY-4.0, and each result carries an infrabase_url that must be used for attribution.

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 core action and scope, followed by the returned-field inventory and licensing notes. The long field enumeration is dense but each item earns its place since there is no output schema.

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 usefully enumerates the returned fields and the attribution requirement, and annotations cover the safety profile. It stops short of describing error behavior for an unknown slug or the response shape beyond field names.

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 schema already explains that slug accepts an Infrabase slug, a product name, or a domain. The description adds nothing about the parameter, so the baseline of 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 (Get) and resource (the full Infrabase.ai record for one AI infrastructure product) and enumerates exactly what the record contains. This clearly separates it from search_tools, which returns slugs rather than full records.

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 explicitly says when to call this tool or that it should follow search_tools. The linkage exists only in the slug parameter's schema text ('as returned by search_tools'), so the usage pattern is implied rather than stated in the description itself.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: hand-verified data, CC-BY-4.0 licensing, and an attribution obligation via infrabase_url. Pagination/result-size behavior is not disclosed, keeping 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?

Three tight sentences, front-loaded with purpose and scope, then narrowing options, then licensing/attribution. Every sentence earns its place with 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?

With no output schema, the description helpfully notes that each result includes an infrabase_url, covering the most important return detail. However, the broader result shape (fields returned) and result-count/pagination behavior are not described, so it is nearly but not 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 100% with both parameters enumerated and documented, so the schema does the heavy lifting. The description only restates that results can be narrowed by category or job, adding no syntax or semantics beyond the schema. 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 (list), resource (AI infrastructure providers), and a sharp scope qualifier (headquartered in Europe). This scope cleanly distinguishes it from siblings like search_tools or list_models without needing to name 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?

Gives clear usage context ('for data residency and sovereignty questions') and notes the optional narrowing dimensions (category or job). It does not name alternatives or state when NOT to use it, so it falls 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 readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds non-obvious behavioral context beyond that: data is hand-verified, results are CC-BY-4.0, and each row carries an infrabase_url for attribution obligations. It does not disclose pagination or result-set size for 'every AI model.'

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 dense sentences, front-loaded with the core purpose and the sibling relationship before license/attribution details. Every sentence carries information, though the CC-BY-4.0 and attribution notes are packed tightly enough that they read as a 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 no parameters and no output schema, the description compensates well by enumerating the result fields (slug, provider count, cheapest provider, infrabase_url). It is close to complete for a simple list tool, missing only pagination or scope caveats implied by 'every AI model.'

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, so the schema has nothing to explain and the baseline of 4 applies. The description usefully clarifies that the returned slug is the input token for model_prices, adding meaning to the output rather than the input.

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 ('List every AI model with verified per-provider pricing') plus the exact fields returned (slug, provider count, cheapest provider). It clearly differentiates itself from the sibling model_prices by positioning itself as the index that produces the slug model_prices consumes.

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 explains the relationship to the sibling tool: 'The slug is accepted by model_prices, which returns the full price table,' which tells the agent this is the discovery step before fetching prices. There is no explicit when-not-to-use clause or guidance on the other siblings (find_alternatives, get_tool), so it stops short of full 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?

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive). The description adds substantial behavioral context beyond them: the ranking rule (cheapest first by blended 3:1 input:output cost), the exact row contents, the verification date, and licensing/attribution terms.

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?

Roughly four sentences that are dense but front-loaded with the core purpose and ranking rule. The license/attribution sentences are somewhat secondary but still earn their place as return-value context.

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 carries the burden of describing return values and does so thoroughly (prices, currency, source page, verification date, attribution URL). The main gap is the lack of explicit alternative-tool routing.

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 both parameters are already documented in the schema. The description adds no syntax or format details for 'model' or 'eu_only' beyond what the schema provides, 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 and resource ('Verified per-token prices for an AI model across hosting providers') with clear scope. The description is precise about what is returned and how it is ranked, but it never explicitly names a sibling (e.g., list_models, find_alternatives) to differentiate itself.

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 gives no when-to-use or when-not-to-use guidance. It neither names alternatives nor states the condition that would select this tool over list_models or find_alternatives, leaving routing to inference.

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 (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description discloses what actually happens: the user's email is sent externally to Infrabase, a human replies by email, and no charge is incurred. This is exactly the extra context annotations cannot carry.

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 purpose, then precondition, then cost/effect disclosure. 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?

Covers purpose, precondition, data handling, response mode, and cost for a non-destructive mutation with no output schema. The only gap is that it does not resolve which of product/product_url/product_name to supply, though the schema hints at this via per-field descriptions.

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 60%, with email/message/product_name undocumented. The description clarifies the side effect of the email parameter (it is forwarded to a third party) but does not explain the product vs. product_url vs. product_name branching (listed vs. not-yet-listed paths), leaving the agent to infer the schema's wording alone.

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 ('Sends a featured-listing request for a product to Infrabase.ai'), and names the recipient service. Siblings are mostly read/list tools (list_models, search_tools, model_prices), so this mutation tool is clearly distinguishable.

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 an explicit precondition: 'Call it only after the user has confirmed.' It does not name the sibling featured_listing_info as the informational alternative, but the timing guidance is clear and actionable.

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, and closed-world, so the safety profile is covered. The description adds genuinely useful non-schema context: the returned field set, the total match count, CC-BY-4.0 licensing, and the attribution requirement tied to infrabase_url.

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 core purpose and coverage before detailing filters and return fields; no sentence is wasted. It is slightly dense in enumerating domains, but the ordering is appropriate for scanning.

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 usefully enumerates returned fields and the total match count, and covers the slug-to-sibling handoff plus attribution terms. Pagination params exist but their behavior is implied by the schema alone, which is acceptable.

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% with two enums fully documented inline, so the schema does the heavy lifting. The description restates the filter axes (free text, category, job, EU HQ) but adds no syntax, matching behavior, or interaction rules beyond what the schema already provides.

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 Infrabase.ai, a hand-verified directory of AI infrastructure products') and enumerates the domain coverage. It clearly distinguishes itself from siblings like get_tool and find_alternatives by positioning those as downstream consumers of the slugs this tool returns.

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?

Names the filter axes (free text, category, job, European HQ) and explains the search_tools -> get_tool / find_alternatives workflow, which is good routing context. It stops short of explicit when-not guidance or stating which sibling to prefer for other lookup patterns.

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