sponsorable

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

Beyond the idempotentHint annotation, the description explicitly states that adding an existing item is a no-op, reinforcing idempotency. It also clarifies non-destructive 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?

Three short, front-loaded sentences with no extraneous information. Each sentence adds value.

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 simple add operation with three required parameters and no output schema, the description covers the action, idempotency, and parameter mapping. It does not mention return value, but this is acceptable given no output 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?

The description adds nuance to item_id by mentioning 'Pro plans' for podcasts, which is not in the schema. However, the schema already has a similar description for item_id, so the additional value is modest.

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 'Add an item to a saved list' with a specific verb and resource. It details valid item_id types, distinguishing it from sibling tools like remove_list_item.

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?

While it mentions the tool is idempotent and safe ('Free to call'), it lacks explicit guidance on when not to use it or compare with alternatives like remove_list_item.

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 non-readOnly and non-destructive. Description adds 'Free to call' hinting at no cost, but lacks details on idempotency or duplicate handling.

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 concise sentences, front-loaded with action, no unnecessary words or repetition.

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 simple creation tool with one param and no output schema, the description is partially complete. Missing mention of returned list ID or confirmation.

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 covers 100% and includes a helpful example for 'name'. Description adds no additional parameter context, so baseline score is 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?

Description clearly states verb 'Create' and resource 'saved list', specifies 'empty' to distinguish from add/delete siblings. 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?

Only states 'Free to call', implying safety, but does not explicitly guide when to use this tool vs alternatives like add_list_item or delete_list.

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?

Adds context beyond annotations: 'cannot be undone', user confirmation step, and the constraint on the confirmed parameter. Annotations already indicate destructiveHint=true, but description enriches understanding of consequences.

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, front-loaded with action and consequence. Every word earns its place. Efficient and clear.

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 destructive nature, no output schema, and no nested objects, the description covers all essential information: permanence, user confirmation requirement, and parameter usage. Agent can safely invoke the 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 coverage is 100%, so baseline is 3. The description for list_id ('from list_lists') adds minor context, and the confirmed parameter description restates the schema. No significant semantic addition beyond what the schema 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?

Clearly states 'permanently delete a saved list and everything in it', specifying the verb (delete) and resource (saved list). Distinguishes from sibling tools like remove_list_item (item removal) and create_list (creation).

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?

Explicitly instructs to confirm with the user before calling and to set confirmed=true. Lacks explicit when-not-to-use or alternatives, but the destructive nature and confirmation requirement are 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, idempotentHint, and destructiveHint. The description adds beyond this by specifying the output is a citable document and that the tool is for deep-research/Responses-API compatibility, which is useful context. No contradiction with 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?

Two sentences with no waste. The main action is stated first, followed by clarification on the parameter and an alternative. Every sentence adds value, and the structure is 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?

Given the tool's simplicity (one parameter, output schema provided), the description is fully complete. It explains the purpose, the input format, the output type, and alternatives. No 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 schema covers the 'id' parameter with a description, and the description reinforces this by explaining it is a sponsor domain from search and providing an example. This adds practical meaning beyond the schema alone, and with 100% coverage, the baseline is 3, so a 4 is warranted.

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 retrieves a 'Sponsorable profile' as a 'citable document', using a specific verb and resource. It explicitly distinguishes from sibling 'get_sponsor' by noting that one returns structured JSON, ensuring no confusion.

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 provides an explicit alternative ('For a structured JSON profile use get_sponsor instead'), guiding the agent on when to use this tool versus the sibling. It lacks a broader 'when not to use' but covers the key alternative.

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?

Adds behavioral context beyond annotations: falling back to category sponsors, each result carries a short reason, and the account-linked limitation. No contradiction with annotations (readOnlyHint, idempotentHint, destructiveHint).

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 concise sentences that front-load the core function and fallback, followed by result characteristics and usage hints. No unnecessary words.

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 input modes, fallback, result content, limitations (no browsing, account-linked), and usage scenario. Output schema exists, so return values are handled there. Complete for a query 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?

Input schema has 100% description coverage, so baseline is 3. The description adds value by explaining that either parameter can be used and the fallback logic, but it does not introduce new parameter details 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 verb 'return brands' and the resource 'podcast via name or RSS feed URL'. It also explains the fallback behavior when exact sponsors are few, distinguishing it from siblings like 'search_sponsors' or 'get_sponsor'.

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?

Explicitly states when to use: 'who would sponsor my show?' questions. Provides constraints: one show per call, does not browse catalog, and notes the limitation about linked accounts for sponsor coverage.

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 mark it as readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds 'Free to call' and mentions return content (totals, top sponsors, podcasts) but does not disclose pagination, rate limits, or data freshness. It adds some value beyond annotations but is 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?

The description is two sentences, directly states the purpose and adds a cost note. No unnecessary words, front-loaded with the main 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 (single param, read-only, no output schema), the description adequately covers the return content (totals, top sponsors, podcasts). Minor gap: not specifying if 'top' means a fixed number or all. Overall mostly 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 100% and the single parameter 'slug' is well-documented in the schema. The description does not add additional meaning beyond what the schema provides, so baseline 3 is 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 clearly states 'Category dossier: totals plus the top sponsors and podcasts in the category', which specifies the verb (get a dossier) and resource (category), and distinguishes from siblings like list_categories (just list) and get_podcast/get_sponsor (single entity).

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 fetching detailed category info but does not explicitly state when to use this tool versus alternatives (e.g., list_categories for a list, or other detail tools). It says 'Free to call' but that's more cost than usage 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?

The description adds context beyond annotations: it explains that contacts follow masking/reveal rules and that no credits are charged for deduplicated internal usage. Annotations already indicate idempotency and non-destructiveness, so the description enriches behavioral understanding.

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 efficiently convey the tool's purpose and key behavioral detail. No unnecessary words; the main content is front-loaded.

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 no output schema, the description adequately explains the return contents and special contact behavior. Missing elements like pagination or error handling for missing list_id are minor, but the tool is simple and the description covers the core.

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 input schema already provides 100% coverage for the single parameter list_id, including a description referencing list_lists or create_list. The tool description does not add further meaning to the parameter beyond what the schema offers.

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 'Full contents of a saved list' and enumerates the specific components: sponsors, podcasts, categories, and contacts. This directly addresses what the tool does and differentiates it from siblings that return individual elements (e.g., get_podcast, get_category).

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 mentions that contacts follow similar rules as list_sponsor_contacts, implying when to use this tool for a comprehensive view versus a contacts-only retrieval. However, it does not explicitly state when to use this tool vs alternatives or provide 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 provide readOnlyHint, idempotentHint, destructiveHint. Description adds 'Free to call' and lists profile contents, but doesn't go beyond annotations significantly.

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, no waste, front-loaded with the core 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 low complexity (1 param, no output schema), description covers output content and cost, adequate for selection and invocation.

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?

Only one parameter with full schema description (100% coverage). Description adds no additional meaning beyond schema, meeting baseline of 3.

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?

Description clearly states tool returns full podcast profile with overview, host contact, top/new sponsors. Distinguishes from siblings like search_podcasts and get_sponsor.

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?

Specifies 'Free to call' implying no cost, but lacks explicit when-to-use vs alternatives. Context is clear but 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, idempotentHint, and destructiveHint. The description adds valuable behavioral context: without a linked account, only public sponsors resolve with limited data (no company details, contact section). This 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 two sentences, each earning its place. The first sentence states purpose and contents; the second explains the constraint. No wasted words, front-loaded with key action and resource.

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-sponsor retrieval tool with an output schema (not shown), the description sufficiently covers what the tool does, what it returns, and under what conditions. Annotations provide safety profile. No gaps given the tool's simplicity.

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 a concrete example ('e.g. athleticgreens.com') and clarifies that the domain is the addressing mechanism, enhancing understanding beyond the schema's generic 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 clearly states it provides a full profile for one sponsor addressed by domain, listing included fields (description, industry, etc.). It distinguishes from sibling tools like search_sponsors by specifying that it targets a single sponsor by domain.

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 mentions that the tool is addressed by domain and describes behavior differences based on linked account status. While it does not explicitly exclude other use cases, the context and sibling tools imply appropriate usage.

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 (readOnlyHint, idempotentHint, destructiveHint), the description adds critical behavioral context: without a linked account, totals cover last 90 days and internal identifiers are omitted. No 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?

Two sentences, front-loaded with primary purpose, second sentence adds usage and behavioral conditions. No extraneous text.

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 no parameters and presence of output schema, the description explains the main output and usage context. It could mention the structure of the tree, but output schema likely covers that. Overall adequate.

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 zero parameters and 100% schema coverage, the description adds context about the output (category tree with sponsorship totals), which is sufficient. Baseline for 0 params is 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 clearly states the tool returns 'the full podcast category tree with per-category sponsorship totals' and explicitly mentions that category slugs feed into search_sponsors and search_podcasts, distinguishing it from sibling tools like get_category.

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 indicates when to use this tool (to get category tree for filtering elsewhere) by mentioning slugs feed search_sponsors and search_podcasts, but does not explicitly state when not to use it or compare to alternatives.

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 idempotentHint=true, so the description's 'Free to call' adds marginal value beyond stating it's safe. No additional behavioral details like rate limits or data freshness.

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 that covers purpose and a key characteristic (free). No fluff, but could be split for readability or include a note about return format.

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 zero parameters and no output schema. The description explains the output as lists with item counts, but doesn't mention pagination, filtering, or ordering. Adequate for a simple list, but missing details an agent might need.

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?

There are no parameters, so baseline is 4. The description does not need to add parameter info, but mentions output details (item counts), which is irrelevant to parameter semantics but does no harm.

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 saved lists with item counts, specifying the kinds of items (sponsors, podcasts, etc.). This distinguishes it from sibling tools like get_list (single list) and create_list (creation).

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 says 'Free to call,' implying no cost, but provides no explicit guidance on when to use this tool versus alternatives like get_list or search. Minimal context about optimal use cases.

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 indicate idempotency and non-destructiveness, but readOnlyHint is false. The description adds value by explaining that calls are free, no credits are charged, and for credit-based plans contacts come masked with disclosure fields. It also mentions internal usage recording, which is a side effect not captured by 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 front-loaded with the core purpose in the first sentence, followed by concise details on plans and behavior. Each sentence is informative and efficient, with no wasted words.

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 simple input schema (1 parameter) and no output schema, the description adequately explains the output (masked/unmasked contacts, disclosure fields) and side effects (usage recording). It is comprehensive enough for an agent to understand the tool's behavior, though it could mention error cases.

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 input schema has one parameter 'domain' with a minimal description ('The sponsor's domain'). Schema coverage is 100%, so baseline is 3. The tool description does not add further details about the parameter, but the purpose clarifies its role.

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 sponsor contacts at a sponsoring company, specifically the likely buyers of podcast sponsorships. It uses a specific verb ('list') and resource ('sponsor contacts'), effectively distinguishing from sibling tools like 'search_sponsors' or 'reveal_contact'.

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 when to use this tool (to get sponsor contacts) and provides context about different plans (credit-based vs. included). It mentions 'reveal_contact' for unmasking, offering an alternative. However, it does not explicitly state when not to use this tool or provide clear 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 provide idempotentHint and non-destructive/non-read-only flags. The description adds that removing a missing item is a no-op, which aligns with idempotency, but does not disclose other behavioral traits.

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 concise sentences front-loaded with purpose. Every sentence adds value with no redundancy.

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 simple nature of the tool (2 required params, no output schema, no nested objects), the description adequately covers behavior, idempotency, and usage context.

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 clear descriptions. The tool description adds no additional meaning beyond what the schema 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?

The description clearly states the tool removes an item from a saved list, distinguishing it from siblings like add_list_item (adds) and delete_list (deletes entire list).

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 notes that removing a non-existent item is a no-op and that the tool is free to call, but does not explicitly contrast with alternatives or state prerequisites.

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?

Discloses credit cost, permanent org-wide unlock, and idempotency (no double charge). This adds significant value beyond annotations, which already indicate destructive and idempotent behavior. No 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?

Description is compact (4 sentences) and front-loaded: first sentence states purpose, then cost, then pre-check, then usage rule. No unnecessary words.

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 all key aspects: cost, permanence, idempotency, pre-check requirement, and user confirmation. With annotations providing additional hints, the description is fully adequate for correct invocation.

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 has 100% coverage, but description adds behavioral context for 'confirmed' parameter (ask user, set true only after authorization). This enhances understanding beyond schema descriptions.

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 action ('reveal a contact's full name, email, and LinkedIn URL') and the resource ('contact'). It distinguishes from sibling tools like list_sponsor_contacts by specifying that this tool reveals hidden details.

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?

Explicit guidance on when to use: check has_email/has_linkedin first, ask user for confirmation unless pre-authorized. This provides clear context for appropriate usage and when to avoid, mentioning alternative (list_sponsor_contacts).

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, idempotent, non-destructive. Description adds that it matches sponsor names and domains, returns citable documents, and that results' IDs can be passed to fetch. 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?

Two sentences with purpose and usage guidance front-loaded. The first sentence is somewhat verbose with 'deep-research/Responses-API compatibility interface' but overall concise.

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 a simple tool with one parameter, strong annotations, and an output schema, the description is complete. It explains the output format (citable documents, IDs) and how to use with fetch.

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?

Only one parameter (query) with schema description coverage at 100%. The description's mention of 'sponsor name, product, or domain' matches the schema's description exactly, adding no extra meaning. Baseline 3 is 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 clearly states it searches a database for brands that sponsor podcasts, and distinguishes itself from sibling tools like search_sponsors and fetch by specifying its role as a simple search that returns IDs for fetching full profiles.

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?

Explicitly tells when not to use this tool and which alternative to use for filtered/paginated search: 'For filtered or paginated search (category, industry, recency), use search_sponsors instead.' Also pairs with fetch.

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 destructiveHint. The description adds: free to call, pagination capped at 100 per page and depth 20, and lists result fields. This adds behavioral context beyond the 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?

Three well-structured sentences: purpose, pagination and result details, and sibling reference. No wasted words; each sentence 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 no output schema, the description explains return fields (podcast_id, name, categories, episode count, etc.) and covers pagination, cost, and limitations. Combined with fully described schema, it is complete for its 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 100%, so the baseline is 3. The description adds high-level context (e.g., filters by name, category, sponsor activity, industry) but does not significantly enhance individual parameter semantics 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 opens with a specific verb and resource: 'Search podcasts by name, category, sponsor activity, or the industry of their sponsors.' It clearly distinguishes itself from siblings by mentioning get_podcast for full profile and implying other search tools for different entities.

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 states it is free to call, provides pagination limits and advice to refine filters instead of deep paging, and directs to get_podcast for a full profile. It does not explicitly list alternatives or when-not-to-use, but the context is clear enough.

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, idempotentHint, non-destructive), the description adds critical behavioral details: pagination limits (default 25, max 100, page depth 20), result fields (domain, name, industry, etc.), and account-dependent restrictions (unlinked accounts limited to 90 days, first page, max 25 results). This comprehensively informs the agent of what to expect.

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 efficiently front-loaded with the core purpose, then covers filters, pagination, result fields, account limitations, and sibling pointers in a logical flow. Every sentence adds distinct value, with no redundant or vague statements. It is appropriately sized for the tool's complexity.

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 complexity (9 optional parameters, pagination, account tiers, sibling tools), the description is remarkably complete. It covers filter semantics, pagination caps, result shape, unlinked-account restrictions (90-day window, first page, 25 max), and explicitly references sibling tools for related tasks. The output schema exists, so return-value details are not needed.

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?

All 9 parameters are well-documented in the schema, so schema coverage is 100%, baselining at 3. The description adds value by clarifying the interaction ('All filters are optional and combine (AND)'), explaining that 'category' expects a slug (guiding to list_categories), and that 'industry' is loosely matched free text. This context aids correct usage beyond the schema's individual descriptions.

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's purpose: 'Search companies that sponsor podcasts.' It distinguishes from sibling tools like get_sponsor and list_sponsor_contacts by specifying what each handles. The description also details result fields and pagination, ensuring the agent knows exactly what this tool does versus alternatives.

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 provides explicit guidance on when to use this tool versus alternatives: 'For one company's full profile use get_sponsor; for its buyer-contact list use list_sponsor_contacts.' It also explains filter combination ('All filters are optional and combine (AND)'), pagination limits (page depth capped at 20), and account-specific behavior (linked vs unlinked). This gives the agent clear decision criteria.

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