Top 11

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

No annotations are provided, so the description carries the full burden. It does disclose a concrete behavioral trait — a fixed result size of 11 providers returned as one list — which is genuinely useful. It says nothing about permissions, whether results are ranked by any stated criterion, or behavior when no provider fits the segment, so gaps remain.

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 tight sentences with zero waste. The core action and its fixed result count are front-loaded, followed immediately by concrete examples that anchor the query shape.

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 two-parameter lookup with no output schema and no annotations, the description covers what the tool does, how large the result is, and the query style. It stops short of describing tie-breaking, empty-result behavior, or the relationship between slug and segment, but nothing essential to invoking 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 both parameters are already documented in the schema. The description's 'segment/persona/use-case' phrasing broadens the meaning of segment slightly beyond the schema's 'Segment phrase', but adds no syntax, format, or constraint detail, and says nothing about the required slug parameter. 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: returns the top 11 providers best suited to a segment/persona/use-case, with the concrete query examples making the intent unambiguous. However, it never distinguishes itself from near-neighbors like recommend, pick_one, or list_rankings, which an agent would have to disambiguate from the sibling list alone.

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 two query examples ('best CRM for dentists', 'best fractional CFO for AI startups') imply the use case, which is helpful context. But there is no explicit when-to-use vs when-not, and no alternative tool is named, leaving the agent to infer why best_for beats recommend or cheapest for a given query.

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?

With no annotations, the description carries the full burden. It usefully discloses the sort order and a hard output size (Top 11), which are real behavioral traits, but it says nothing about read-only semantics, whether limit caps the list, or return fields.

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 short sentences, front-loaded with the core behavior and the sort order, followed by the optional filter. No filler or 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?

For a simple three-parameter, no-output-schema read tool the description is roughly adequate, but with no annotations and an undocumented 'limit' parameter it leaves gaps an agent must infer, and it never clarifies that results are scoped to the required list slug.

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 67%: 'slug' and 'max_price' are documented in the schema, while 'limit' has no description anywhere. The description adds a small amount of meaning by framing max_price as an optional ceiling filter and connecting the Top 11 cap to the schema's maximum of 11, but 'limit' remains unexplained.

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 action (return cheapest providers) plus the shape of the result (a single Top 11 list sorted by lowest starting price). It implicitly contrasts with siblings like 'fastest' and 'best_for' by declaring 'cheapest', though it never names an alternative directly.

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?

No when-to-use guidance is given relative to the many ranking/selection siblings (list_rankings, best_for, compare, pick_one). The only usage signal is that max_price is optional, which does not help an agent choose this tool over 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?

With no annotations, the description carries full behavioral burden. It helpfully lists the output fields (rank, score, pricing, verdict, pros, cons, winner), which is valuable given no output schema, but it does not state that this is a read-only operation or mention any side effects, permissions, or rate limits.

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 zero waste; the core purpose is front-loaded and the return information follows immediately.

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, lack of annotations, and no output schema, the description adequately covers what it does and what it returns. The only gap is the absence of usage guidance relative to sibling tools.

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 (a and b) are fully documented in the schema itself. The description adds no additional meaning beyond 'by brand name,' which the schema already conveys.

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 (compare) and resource (two ranked providers), and the side-by-side framing clearly distinguishes it from siblings like recommend, pick_one, and best_for.

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 implies the tool is for comparing two providers by brand name, but offers no explicit when-to-use guidance or alternatives. Siblings like pick_one or recommend are not referenced, leaving the agent to infer the context.

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?

No annotations are provided, so the description carries the full behavioral burden. It does not explain what 'Top 11' means (ranking basis, ordering, tie-breaking), whether results are paginated, or any auth/rate-limit constraints. It confirms a read-style list operation only implicitly.

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. Efficient, though 'Top 11' is an oddly specific claim that it does not support with any explanation.

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 annotations and no output schema, the description should do more work. The 'slug' parameter is undocumented, the 'Top 11' ranking logic is unexplained, and nothing covers return shape or ordering — significant gaps for a 2-required-param filtering 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 0%, so the description must compensate for both parameters. It enumerates the certification values, but that merely repeats the enum already in the schema, and it never explains 'slug' — the more ambiguous parameter, whose referent (provider? list? category?) is left entirely undefined.

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 (Return) and resource (Top 11 providers holding a specific compliance certification), which makes its function legible despite the opaque tool name 'compliant'. It does not, however, differentiate itself from sibling filter tools like in_region or works_with, leaving the agent to infer the distinction.

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 guidance on when to use this tool versus the many sibling filtering tools (in_region, works_with, best_for, etc.). No prerequisites or exclusions are stated, so the agent must guess at the selection criteria.

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?

With no annotations, the description carries full responsibility for behavioral disclosure. It says nothing about return format, pagination, authentication needs, or how the 'slug' parameter influences the result. It appears to describe a fixed ranking that is unrelated to the required 'slug' input, leaving a significant gap.

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, well-formed sentence that front-loads the operation. There is no unnecessary text; it is appropriately 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 no annotations, no output schema, and a required parameter entirely undocumented, the description is incomplete. It doesn't explain what the 'slug' is for or what the output looks like, leaving an agent unable to call the tool correctly without guessing.

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 0% and the description does not explain the 'slug' parameter at all. For a required parameter, this is critical missing information; the parameter's role and acceptable values are completely undocumented.

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 ('return') and resource (top 11 providers) with a clear ranking criterion (quickest onboarding time). Distinguishes itself from siblings like 'cheapest' and 'best_for' by naming the concrete metric. However, it doesn't explicitly handle the required 'slug' parameter, which is used only for the ranking category, making the purpose slightly ambiguous when the input doesn't match the output.

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?

No indication of when to use this tool versus alternatives such as 'cheapest' or 'list_rankings'. The description doesn't mention any conditions, exclusions, or prerequisites for invoking it.

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?

With no annotations, the description carries the full behavioral burden, and it only discloses the result cap ('Top 11') and the free-tier/free-trial distinction. It omits how 'Top' is ordered, whether results are ranked or paginated, and any auth or rate-limit context.

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 the action and capped by the essential disambiguation. Every clause earns its place with no boilerplate.

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 one-parameter query tool with no output schema, the description covers the criterion and result count but leaves the ordering basis and the meaning of the required slug unexplained. Adequate as a minimum viable statement, not self-sufficient.

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 0% and the single required 'slug' parameter is never described. The tool's list-oriented purpose implies slug identifies the list to query, but format, requiredness, and accepted values are left entirely to inference.

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 ('Return Top 11 providers') plus the exact criterion (free tier, explicitly not a free trial). That parenthetical disambiguates the concept well, but it never names or contrasts any sibling tool (cheapest, fastest, compliant), so an agent must infer this sits in a family of criterion filters.

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?

No when-to-use guidance: the description does not say when to pick free_tier over cheapest, best_for, or recommend, nor what the required slug must identify. The '(not a free trial)' clause is a semantic clarification of the criterion, not usage routing.

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?

With no annotations, the description carries the full behavioral burden, yet it discloses nothing about error behavior for a nonexistent slug or out-of-range rank, whether the list must exist first, or the shape of the returned entry. Only the rank range is mentioned, and that is already in the schema.

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 front-loaded sentence with zero filler; the resource, key, and value range all appear before any padding could.

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 and no annotations, so the description is the only guidance an agent gets. For a simple two-parameter lookup it is close to sufficient, but it omits failure modes and return structure.

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 0%, so the description must compensate. It clarifies that slug identifies the Top 11 list and rank selects an entry within it, which is more than the bare schema types, but it says nothing about slug format or whether rank is 1-based ordering semantics.

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?

Specific verb+resource: returns a single ranked entry from a Top 11 list, keyed by slug and rank. The 'single ... entry' phrasing implicitly separates it from the sibling get_list, though it never names that sibling explicitly.

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: you call this when you want one entry rather than the whole list. No when-not conditions, prerequisites, or named alternatives (get_list, list_rankings) are given despite several plausible siblings.

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?

No annotations are provided, so the description carries the full behavioral burden. It does disclose the return payload shape (11 entries with scores, verdicts, pros/cons, pricing), which is real value given there is no output schema, but it says nothing about auth, unknown-slug behavior, or error/failure modes.

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 the action and resource, and every clause (scope, identifier, payload contents) carries information an agent needs. 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?

For a one-parameter read tool with no output schema, the description usefully summarizes the return shape, so the agent knows what it gets back. The only remaining gap is behavior on invalid or unknown slugs, which is minor here.

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 'slug' parameter is documented with a format example in the schema itself. The description only restates that the slug identifies the list, adding no new syntax or constraint information. 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 ('Return') and resource ('the full structured ranking for one Top 11 list by slug') and enumerates the payload contents. The scope word 'full...list' cleanly distinguishes it from single-entry siblings like get_entry.

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 the scope: 'one list by slug' suggests use when you have a slug and need everything. There is no explicit when-to-use, no when-not-to, and no named alternative such as list_rankings for discovery or get_entry for a single 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?

No annotations exist, so the description carries the full behavioral burden and does not meet it. It implies a read operation ('Return') but never states what 'Top 11' is ranked by, whether results are ordered, capped, paginated, or what happens if no providers match. The undefined ranking criterion is a meaningful behavioral gap.

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 efficient sentence with the core purpose front-loaded and no filler. It is arguably over-terse rather than padded, but on the conciseness axis itself it is clean.

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 2-required-param tool with no annotations, no output schema, and 0% schema coverage, one sentence is inadequate. Missing the meaning of the required slug, the ranking basis for the 'Top 11', and any indication of result shape or ordering.

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 0%, so the description must compensate and does not. It restates the region enum values already in the schema (no added value) while the required 'slug' parameter is completely undocumented in both the schema and the description — an agent cannot know what list or entity the slug refers to.

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 clear verb ('Return') and resource ('Top 11 providers serving a region'), and 'serving a region' distinguishes it from criterion-based siblings like cheapest or best_for. However, it never names those siblings or explains how this tool relates to them, so differentiation is only implied. The 'Top 11' qualifier is oddly specific without explaining the ranking basis.

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?

No when-to-use guidance at all. With 13 siblings (best_for, cheapest, fastest, free_tier, compare, etc.), an agent has no signal about when filtering by region is the right choice versus picking by criterion. No prerequisites or exclusions are 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?

No annotations are provided, so the description must carry the full behavioral burden. It implies a read-only listing by using 'List' and specifies the dataset ('every published Top 11 ranking') and returned fields, but does not explicitly confirm read-only safety, pagination behavior, or ordering. For a zero-parameter list tool this is minimally adequate but lacks explicit behavioral context.

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 front-loads the verb and resource, then parenthetically lists the returned fields. No filler or 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?

With no output schema and no annotations, the description must cover return values and safety. It names the three returned fields, which is useful, but does not specify ordering, pagination, or explicit read-only behavior. For a simple list tool this is largely complete but not exhaustive.

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 no parameters, so the baseline is 4 per the rubric. The description mentions returned fields (slug, title, last-verified date), which is output rather than input semantics; the empty schema leaves no parameter meaning to add.

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?

Specific verb 'List' and resource 'Top 11 ranking' with scope 'every published' and output fields. It does not differentiate from sibling tools such as get_list or recommend.

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?

No guidance on when to use this tool versus siblings like get_list or best_for, nor any prerequisites or exclusions. The description only states what it lists.

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?

With no annotations, the description must carry the behavioral burden. It does add genuine provenance context — verdicts are hand-researched and prices are read on each vendor's own site, and a vendor URL accompanies every price. But it says nothing about permission/auth needs, result size, or pagination behavior for the no-slug call that returns every verdict.

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?

It front-loads the user-facing question and the core deliverable, then closes with the calling instructions. The middle sentence is dense with a three-item deliverable list but every clause carries information. No filler or restated title to trim.

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 annotations, no output schema, and a single optional parameter, the description supplies enough: what is returned (verdicts, per-buyer-type winner, comparison table, sourced prices) and how to invoke both modes. The remaining gap is behavioral limits on the all-verdicts call, which is minor for a read-only 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?

Only one parameter and schema coverage is 100%, so the baseline would be 3. The description goes beyond the schema's terse 'Optional list slug or compare slug' by giving concrete example values ('tms-for-freight-brokers' and 'quickbooks-vs-xero-vs-freshbooks'), which clarifies the two distinct slug vocabularies an agent must choose between.

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 concrete deliverable: hand-researched verdicts on the top three of a Top 11 list, a named winner per buyer type, a side-by-side table, and a sourced vendor URL for every price. That is specific enough for an agent to know what comes back. It does not, however, contrast itself against near-neighbors like 'best_for', 'recommend', or 'compare', so differentiation is left to inference.

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 clearly explains the two invocation modes: call with no slug for every verdict, or pass a list slug / compare slug for the full comparison. That is useful call-shape guidance but it is not when-to-use guidance — nothing tells the agent why to choose this over 'recommend' or 'compare', and there are no exclusions or 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?

With no annotations, the description carries the full burden and does well: it discloses the return content (top matches, the reason each was chosen, each pick's risk level) and the filtering behavior (max_risk excludes firms with higher verified public risk signals). It omits any auth/permission or rate-limit notes, which is a minor gap for a read-only lookup.

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, then optional parameters, then the return shape. The parenthetical examples add length but earn their place by showing expected input style; overall dense but not wasteful.

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 6-parameter, enum-bearing tool with 100% schema coverage and no output schema, the description covers invocation, filtering semantics, and return contents, so an agent can call it correctly. The main unfilled gap is sibling disambiguation against recommend_across_lists.

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, but the description adds genuine meaning beyond the schema: budget band syntax ('$', '$$', '$$$'), the semantics of max_risk as a ceiling that excludes higher-risk firms, and examples of 'problem' phrasing. This exceeds the schema's terse field 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?

States a specific verb+resource ('hand over a user's situation and get the best-matched picks') and clarifies scope via the Top 11 list and auto list-selection. It does not, however, differentiate itself from the very similar sibling 'recommend_across_lists', leaving the agent to infer which to call.

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 invocation context — describe the problem in plain language with concrete examples, and notes 'No slug needed' since the list is auto-picked. There are no explicit when-not conditions or named alternatives (e.g. vs recommend_across_lists or pick_one).

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?

No annotations exist, so the description carries the full burden. It does disclose real behavioral traits: the candidate pool is every published Top 11 list and results are ranked by relevance. However it says nothing about the response shape, whether results are cached/read-only, or how limit/budget interact with the ranking.

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 filler, and the mechanism (what it pulls) is front-loaded before the usage condition. Every clause 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?

For a simple 3-parameter read tool with a required 'problem' input, the description covers what it does and when to use it adequately. The one remaining gap is that, with no output schema present, it never sketches what a returned recommendation looks like.

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 only 33%: 'budget' is documented in-schema, while 'limit' and 'problem' have no descriptions. The description partially compensates by explaining that ranking is by relevance to the problem, and limit's bounds are already expressed structurally via min/max 1-11, but it never clarifies that limit caps the returned candidate count or how budget filters candidates.

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 gives a specific verb+resource ('Cross-list recommendation: pulls candidates from every published Top 11 list') and a ranking basis ('ranked by relevance to the problem'). It implicitly contrasts with the sibling 'recommend' by emphasizing the cross-list/every-published-list scope, though it never names that sibling explicitly, so the differentiation requires a small inference.

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?

'Use when the user's problem could span multiple categories' is a clear, actionable positive trigger. It stops short of stating when *not* to use it (e.g. a single-category problem, where the sibling 'recommend' or 'pick_one' would apply), so no explicit alternative is named.

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?

With no annotations, the description carries the full behavioral burden. It discloses the result cap ('Top 11') but says nothing about ranking criteria, ordering, behavior when the tool is unknown, or whether results are filtered or paginated.

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 the return shape stated first and examples parenthetically. No filler; it could only be improved by adding the missing usage and parameter 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?

No output schema or annotations exist to offload information, and the slug parameter's role is unexplained, so the definition is thin for a two-required-param tool. The stated 'Top 11' return helps, but an agent still lacks context on input format and ranking semantics.

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 50%: 'tool' has a trivial description ('Tool name.') while 'slug' is undocumented in both schema and description. The description does add real value by giving example tool values (QuickBooks, NetSuite, Salesforce, Open Dental), but leaves the meaning of 'slug' entirely ambiguous.

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 (return) and resource (providers that integrate with a named tool), plus a concrete result shape (Top 11). It is clearly distinguishable from ranking siblings like cheapest or compliant, but never explicitly contrasts itself 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?

No when-to-use guidance, no prerequisites, no mention of alternatives such as best_for or recommend, even though the sibling set is full of similar selection tools. The agent must infer usage entirely from the name.

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