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

With no annotations, the description carries the full load; it does disclose meaningful boundaries — the tool never commissions work and has no spending authority, and its output is a bounded task plus an official handoff. However it never states whether the operation is read-only, what artifact the handoff is, or what the caller receives, leaving the behavioral profile partly inferred.

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?

There is no filler and the word count is low, but the sentence is telegraphic to the point of being under-specified — 'consider Basic' and 'official handoff' are unexplained shorthand. Brevity here buys density at the cost of parseability.

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, no annotations, and a six-field nested input where zero fields are documented; the description should at minimum say what verdict/artifact the assessment emits and what the boolean flags gate. Neither is covered, so an agent cannot reliably construct the request or interpret the result.

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% for a nested request object containing six fields (product_urls, sources_permitted, recurring_cloud_need, existing_api_or_export, local_execution_sufficient, sensitive_or_login_required), most of which are ambiguous without prose. 'Based on need' faintly implies the booleans encode need factors, but no field is defined, so the description fails to compensate for the coverage gap.

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 decision outcomes (free / existing API / reject / consider Basic) but never states the subject being assessed — BrowserAct fit is only inferable from the tool name, and 'prepare bounded task and official handoff' muddies whether this is a decision tool or a preparation tool. It is distinguishable from validate_browseract_report/csv only by the word 'Choose', not by any explicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'never commission' and 'No authorization to spend' are hard constraints, not routing guidance; nothing says when to call this instead of recommend_referral_service or prepare_referral_task, nor what precondition (e.g. a scoped task already identified) makes this the right first step.

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 does add meaningful behavioral context: it states no execution occurs, providers are not contracted sellers, and affiliate status/disclosure is explicit. However, it omits permissions, how the six providers are selected, what 'unresolved' means operationally, and what the returned cards contain.

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 short and front-loaded with the list operation and the six-card scope. The remaining clauses are relevant constraints, although the compressed phrasing makes parts of it harder to interpret.

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 no parameters, the description must carry the full burden. It does not explain the output structure, the meaning of the six researched cards, how eligibility/pricing/payout terms are represented, or the affiliate disclosure details an agent would need to interpret results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is nothing for the description to clarify at the parameter level. Baseline 4 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 names a list operation over 'six researched provider cards' with eligibility, prices and payout terms, but 'provider cards' and 'unresolved eligibility' are vague jargon, and the relationship to sibling tools like recommend_referral_service is not clarified. It does distinguish the tool from contracted sellers and execution, which helps somewhat.

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 guidance on when to use this tool versus alternatives such as recommend_referral_service or prepare_referral_task. The phrase 'Not contracted sellers; no execution' is only a weak negative constraint, not when-to-use 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?

With no annotations, the description must carry the full behavioral burden. It does usefully disclose non-mutation boundaries (no execution, no account creation, no secrets, no purchase, no attribution), but it says nothing about how sensitive_data or sources_permitted alter what is returned, nor about rate limits or any permission requirements.

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 that front-load what is returned and then enumerate what is forbidden. No redundant restatement of the tool name, though the second sentence reads as a bare keyword list rather than a rationale.

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 single nested parameter object, no annotations, and no output schema, the description's definition of returned artifacts plus its explicit non-actions covers most of what an agent needs. The main unmet need is the semantics of the two boolean flags.

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 it does not. 'Provider-specific' weakly hints at provider_id, but the two boolean flags (sensitive_data, sources_permitted) are completely unexplained — an agent cannot know whether they gate, redact, or reshape the returned guidance.

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 the outputs (provider-specific task, example, output fields, official connection steps), which tells the agent the tool produces preparatory guidance rather than performing anything. However, 'task' is ambiguous, and it never explains how this differs from list_referral_providers or recommend_referral_service, which sit in the same referral workflow.

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: the negative list ('no execution, account creation, secrets, purchase or attribution') signals that this is a pre-execution information step, likely after a provider has been recommended. No explicit when-to-use or when-not-to-use-vs-siblings statement is given.

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 does disclose real behavioral policy — no commission-based ranking and that budget is not authorization — which is valuable, non-obvious context. However, it never states whether the tool is read-only/advisory, whether it actually creates a referral, or what it returns, leaving side-effect profile 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?

Three tight clauses, front-loaded with the core matching rule and followed by the two hard constraints. No filler, though the aphoristic phrasing ("Budget is not authorization") costs some clarity in exchange for brevity.

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 annotations, no output schema, and a seven-field nested request at 0% schema description coverage — this is the case where the description should do the most work. It omits the return shape, how sensitive_or_login_required and sources_permitted change the recommendation, and any precondition for obtaining consent before referrals.

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 nested Selection has seven fields, so compensation is needed. The description does add meaning to a few: "explicit need" maps to need, "prefer existing/local" maps to existing_solution_sufficient/local_solution_sufficient defaults, and "budget is not authorization" clarifies maximum_monthly_budget_usd. But the six-value need enum, sources_permitted, recurring_need, and sensitive_or_login_required go entirely 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?

"Match an explicit need to capability" gestures at recommending a provider for a stated need, but the verb is abstract and never names the artifact produced (a ranked recommendation vs. a single provider). It does not distinguish this from siblings like list_referral_providers or assess_browseract_fit, so the agent must infer the boundary.

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?

"prefer existing/local/free" and "reject unsafe scope" give decision policy for ranking, which implies when this tool applies. But there is no explicit when-not guidance and no mention of the sibling tools, so routing between recommend_referral_service and list_referral_providers is left 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?

With no annotations, the description does useful work by declaring what the tool will NOT do: no currency inference, no provider calls, no payment or telemetry, and it preserves original strings. However, it never says what happens on invalid rows, whether validation is all-or-nothing, or what the result looks like, leaving the safe-read profile partly inferred.

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 compact sentences, front-loaded with the core action and the size bound. The negative-constraint clause is dense but each element (no inference, no provider calls, no payment/telemetry) conveys a distinct safety guarantee.

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 annotations, no output schema, and no schema descriptions leave the description as the only information source, yet it omits the origin parameter's semantics and any indication of the validation result shape. For a validation tool, not knowing what 'valid' output looks like is a material gap.

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 partly does — 'max-20-row CSV' maps to csv_text/maxItems and 'expected URLs' maps to expected_urls — but the origin parameter with its internal/allubi/independent_unverified enum is never mentioned, and expected CSV column structure is 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?

States a specific verb and resource: validate a BrowserAct CSV against expected URLs, with a size bound. It is distinguishable from siblings like validate_browseract_report by naming CSV input, though it does not explicitly contrast with that sibling.

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 when-to-use guidance, no mention of prerequisites, and no routing to validate_browseract_report or assess_browseract_fit. The only contextual constraint is the implicit 20-row limit, which is a data constraint rather 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?

With no annotations provided, the description carries the full behavioral burden. It usefully discloses that the tool does not fetch data and does not certify truth, and that errors stay explicit, but it does not describe the validation criteria, return behavior, or what happens when completeness checks fail.

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 compact sentences with no wasted wording. The primary purpose is front-loaded, followed immediately by the key behavioral caveats.

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 must do more work than usual. It establishes the tool's non-fetching and non-certifying nature, but it leaves unclear what 'completeness' means operationally and what the agent should expect back from validation.

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 should compensate for the nested report fields. It partially does by mentioning 'up to 20 product results' and 'supplied samples,' which loosely maps to rows and sample_rows, but it does not explain expected_urls, origin, or engine semantics beyond what the schema patterns provide.

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 and resource: 'Check completeness of up to 20 product results and supplied samples.' That is clear enough for an agent to understand the tool validates a report payload, but it does not explicitly distinguish it from sibling tools like validate_browseract_csv or assess_browseract_fit.

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 by framing the tool as a completeness checker for supplied product results and samples, and it explicitly excludes fetching and truth certification. However, it does not say when to choose this tool over validate_browseract_csv or how it relates to the other referral/browseract siblings.

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