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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the description is not responsible for the safety profile. Beyond annotations it adds essentially nothing – no indication of whether results are capped, how partial-name matching behaves, or whether multiple facets can be queried in one call. The phrase "such as countries" is the only behavioral hint, quietly confirming the default location facet.

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 zero filler and no redundant restatement of the title. It is efficient, though its terseness borders on under-specification rather than optimal density.

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?

An output schema exists and annotations are rich, so the description needn't explain return values or safety. However, the one genuinely agent-relevant fact – that the facet parameter generalizes the lookup beyond locations – is left entirely to the schema, and no relationship to sibling lookup tools is established.

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 all three parameters are already documented, including the facet default URN and the adAccountId allowlist constraint. The description only restates the query concept ("by name") and never explains that the facet parameter makes this tool generic to skills, industries, and other facets. Baseline 3 applies when the schema does the heavy lifting.

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 combination ("look up native targeting URNs") and gives a concrete example ("such as countries by name"), so the agent knows this resolves human-readable names into LinkedIn targeting URNs. It does not distinguish itself from adjacent lookup tools like linkedin_get_entity or linkedin_validate_query, which is the only reason it falls short of a 5.

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: an agent can infer it should call this before any tool that needs a targeting URN. There is no explicit statement of when-not-to-use, no mention of how it relates to linkedin_validate_query or linkedin_list_ad_accounts, and no prerequisites (e.g. that adAccountId must be configured) are surfaced.

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 openWorldHint, so safety is covered. The description contributes one genuinely non-obvious trait — that per-account role grants, not scopes, drive failures — which is useful diagnostic context, but it omits anything about cost, rate limits, or response shape.

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 padding, with the core read action front-loaded before the troubleshooting note. Every sentence carries distinct information.

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?

An output schema exists so return values need no explanation, and the description covers purpose, included data, and failure semantics. Only the absence of any explicit routing to sibling tools keeps it from a 5.

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 both parameters (adAccountId with its LINKEDIN_ADS_ACCOUNT_IDS constraint, and includeUsers defaulting on) are already fully documented. The description's mention of 'members who hold a role' loosely maps to includeUsers but adds no syntax or format detail beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read one LinkedIn ad account in full') and adds the scope detail that member roles are included. It implicitly contrasts with the list-style sibling but never names linkedin_list_ad_accounts, so the differentiation is inferable rather than explicit.

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 single-account framing plus the note that failures are usually role-based gives clear context for when this read is the right call versus a list operation. It stops short of naming an alternative tool or stating 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=false, so the safety profile is covered. The description adds useful domain context about shared budgets and bid strategies living at this level, but says nothing about pagination behavior, result volume, or rate/permission constraints beyond what the schema states.

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, both earning their place: the first front-loads what is returned, the second supplies the conceptual model. No redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, rich annotations, and full parameter documentation, the description only needs to orient the agent, which it does. The only remaining gap is explicit routing versus sibling list tools such as linkedin_get_campaigns.

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 every parameter including name, status, pageSize, pageToken and adAccountId is already documented in the schema. The description adds no additional semantics about filtering behavior (e.g., exact-match name arrays or status filtering), so it sits at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List campaign groups in a LinkedIn ad account') plus the fields returned (budget, schedule, serving status). It also situates the resource in the LinkedIn hierarchy relative to campaigns. It stops short of naming the sibling list tool it complements, so sibling differentiation is implied rather than stated.

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

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

The closing sentence hints at when this level is useful ('explains why sibling campaigns stopped together'), which implies a diagnostic use case. But there is no explicit when-to-use/when-not guidance and no named alternative among the many sibling list/get tools, leaving selection largely 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?

The annotations provide robust technical transparency (read-only, idempotent). The description adds domain-specific behavioral context by explaining that campaigns contain targeting/bidding logic and that creatives are separate, aiding in the agent's conceptual understanding of the LinkedIn ecosystem.

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 definition is brief and efficient. It allocates the first sentence to scope and the second to conceptual architectural context, achieving high information density without becoming verbose.

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 100% schema coverage and rich annotations, the description does not need to cover technical details like return types or parameter syntax. It successfully covers the conceptual completeness by describing the data hierarchy (campaign holds targeting, creatives are ads).

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?

Given that schema coverage is 100%, the baseline is 3. However, the description adds significant semantic value by clarifying the underlying business logic—specifically, that the campaign object encompasses targeting and bid strategies, which is crucial context for an agent building a complex query.

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 purpose is stated clearly as 'List campaigns in a LinkedIn ad account,' immediately identifying the resource and action. The description further enhances this by listing key returned attributes like status, objective, and budget.

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 doesn't explicitly compare itself to siblings, the description details exactly what data is returned (status, objective, format). This helps the agent determine if this tool can fulfill a user's request without needing to call a different tool (e.g., a demographics tool).

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 read-only, idempotent, non-destructive, so the safety profile is covered. The description adds real domain context beyond that: a creative is the ad itself and carries intended status, review verdict and hold-back reasons — information an agent could not get from the annotations or 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?

Two sentences, front-loaded with the operation and scope, with the second sentence earning its place by defining the returned entity. No filler or repetition of schema details.

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 paginated read tool with an output schema and full parameter documentation, the description supplies the entity definition and the interesting payload fields. Minor gap: no mention of pagination behavior or the relationship to the near-identical sibling 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 100%, so all six parameters are already documented, including the native-vs-effective status distinction for intendedStatuses. The description only alludes to campaign scoping and adds no filter syntax or defaults beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the creatives of a LinkedIn ad account') plus the optional campaign scoping, and defines what a creative is. It does not, however, differentiate itself from the sibling linkedin_list_ad_creatives, which reads as a near-duplicate by name.

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 phrase 'optionally for given campaigns' implies the filtering use case, but there is no explicit when-to-use guidance and no routing between this tool and linkedin_list_ad_creatives. Usage is inferable rather than 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?

Annotations already declare the operation read-only, idempotent, non-destructive, and open-world. The description adds useful domain behavior beyond annotations: LinkedIn exposes user status and system serving status side by side, and the system status is usually the one that explains non-delivery.

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 are used with no wasted wording. The diagnostic purpose is front-loaded, followed immediately by the key domain insight about user versus system status.

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 an output schema, complete annotation coverage, and 100% schema descriptions, so return values, safety, and parameters are largely handled elsewhere. The description supplies the crucial diagnostic framing and status interpretation, though it could better distinguish itself from linkedin_health_check.

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 parameter meanings are already fully documented. The description only loosely hints at account-to-creative scope and adds no syntax, constraints, or defaults beyond what the schema provides, making baseline 3 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 states a specific diagnostic verb and resource: explain why LinkedIn ads are or are not serving, scoped from account to creative. It distinguishes itself from retrieval siblings by diagnostic intent, but does not explicitly name alternatives such as linkedin_health_check.

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 first sentence gives a clear diagnostic context: use this when you need to understand why ads are or are not serving. It does not name alternatives or exclusions, so it falls short of the explicit sibling routing seen in a 5.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. The description adds only that limits are stated alongside rows, without specifying what those limits are or any auth/rate-limit detail. It does not contradict 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?

Two sentences, with the purpose front-loaded. The second sentence mixes useful context ('limits ... alongside the rows') with promotional filler ('numbers LinkedIn is bought for'), so it is concise but not waste-free.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only reporting tool with full schema coverage, annotations, and an output schema, the description gives enough to identify the breakdown capability. It omits comparison guidance to sibling reporting tools, which keeps it from a 5.

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's list of demographic categories loosely maps to the breakdown enum, but it does not add syntax or meaning for limit, metrics, campaign filters, resolveNames, or dates 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?

States a specific verb and resource: break LinkedIn delivery down by professional demographics, and lists the available grouping categories. It does not explicitly distinguish this from sibling reporting tools such as linkedin_get_insights or linkedin_run_statistics_report, so it falls short of a 5.

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?

Implies the tool is for demographic breakdown reporting by naming the professional demographic dimensions. It gives no explicit when-to-use guidance, alternatives, or exclusions compared with sibling reporting tools; usage is only implied.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description contributes the ownership-verification detail, which tells the agent a permission check is part of the call. It adds nothing about failure behavior when ownership fails or about openWorld-related variability, so it is a modest increment over 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?

A single short sentence that front-loads the verb and the resource scope with zero filler. It is efficient, though slightly too terse to carry usage routing or behavioral nuance.

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 is a simple three-parameter read with 100% schema coverage, full annotations, and an output schema that covers return values. Given that, the description is adequate: it names the entity kinds and the ownership check. Minor gaps remain around choosing this over sibling list/get 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%, and the schema already documents the kind enum, the entityId pattern including the sponsoredCreative URN form, and the account ID constraint. The description only restates the ownership verification that the entityId schema description also mentions, so it adds no semantic value beyond structured fields.

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 and resource set (read one campaign group, campaign, or creative), which is clearly distinct from the plural list siblings such as linkedin_get_campaign_groups and linkedin_get_campaigns. It stops short of naming those siblings as alternatives, so differentiation is implied by the singular noun rather than stated.

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

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

The phrase 'read one' implies this is the single-entity fetch path and that the list tools cover bulk retrieval, and 'verify account ownership' hints at a post-lookup access check. However, there is no explicit when-to-use versus the list tools, no guidance on choosing between it and linkedin_get_account_details, and no preconditions spelled out beyond what the schema already encodes.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds genuinely non-structured behavior: ratios like CTR, CPC and CPM are not API-native and are computed here from raw terms, which explains why returned fields may include values absent from the metrics vocabulary. It omits row limits and pagination behavior for a report tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with the core action front-loaded and no filler. The computed-ratios sentence earns its place; the middle sentence is somewhat redundant with the first.

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 12 parameters at full schema coverage, rich annotations, and an output schema that documents return values, the description need only cover purpose and the non-obvious computed-metrics behavior, both of which it does. The unresolved sibling ambiguity is scored under usage guidelines rather than completeness.

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

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

Schema coverage is 100%, so the schema carries parameter documentation and the baseline is 3. The description adds only loose framing ("one pivot, any granularity"), and its claim of "up to 20 fields" conflicts with the schema's maxItems: 40 for metrics, which could mislead about capacity; note this is a schema inconsistency, not an annotation contradiction.

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: "Run a LinkedIn Ads report grouped by one pivot," and adds a scoping phrase ("the analytics finder"). It distinguishes this from entity-listing siblings, but does not name or distinguish it from linkedin_run_statistics_report or linkedin_get_demographics, which occupy overlapping territory.

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 implied rather than stated: "one pivot, any granularity" tells the agent the shape of appropriate requests. There is no explicit when-to-use/when-not guidance and no routing rule pointing to linkedin_run_statistics_report or linkedin_get_demographics, so the agent must infer the choice from name alone.

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 annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is largely covered. The description adds that the tool refreshes a URL and verifies library association, which is useful behavioral context beyond the annotations. However, it does not explain what 'refresh' means operationally (e.g., signed URL retrieval) or what verification entails.

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, front-loaded sentence with no wasted text. It could be slightly clearer about the tool's return behavior, but its brevity suits a simple two-parameter lookup tool.

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 rich annotations, complete input schema, and an output schema, the description does not need to explain return values or safety properties. Still, it leaves a clear gap around when to choose this tool over linkedin_list_media and what exactly 'refresh' and 'verify library association' produce.

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 required parameters (mediaId and adAccountId) are fully documented in the input schema. The description does not add any parameter-level details beyond what the schema already provides, so the baseline score of 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 states a specific action for a specific resource: refreshing one image/video URL and verifying its library association. However, the name 'get_media' suggests retrieving media details, while the description emphasizes 'refresh' and 'verify', leaving some ambiguity about what the tool actually returns. It does not explicitly distinguish itself from the sibling linkedin_list_media.

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

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

The description gives no explicit guidance on when to use this tool versus alternatives such as linkedin_list_media or linkedin_get_creatives. The phrase 'one image/video URL' implies a single-item lookup, but there are no stated prerequisites, exclusions, or alternative-selection rules.

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 the safety profile (read-only, idempotent, non-destructive, open-world). The description adds meaningful behavioral context beyond annotations by stating the CRM dependency and the enforced 30–366 day window, which materially affect whether and how the tool can be called.

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 compact and front-loaded: it starts with the report identity, then states the key eligibility constraints. Every clause contributes useful information with no wasted phrasing.

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 rich annotations, 100% schema coverage, and an output schema, the description covers the essential context: what report it returns, the CRM prerequisite, and the date-window limit. It could be slightly more complete with explicit sibling routing or filter behavior, but it is sufficient 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 description coverage is 100%, so the input schema already documents all six parameters, including defaults and constraints. The description reinforces the date-window constraint but adds no extra parameter-level meaning beyond what the schema provides, making 3 the appropriate baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific report and clearly defines its content: CRM pipeline and closed-won revenue attributed to LinkedIn advertising. This is a distinct resource from generic insights/statistics tools in the sibling list, so an agent can identify what the tool does without opening the schema.

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

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

It gives clear eligibility and constraint guidance: the account's Business Manager must have a CRM connected, and the reporting window must be 30 to 366 days. It does not explicitly compare this tool to siblings like linkedin_get_insights or linkedin_run_statistics_report, so it falls short of full when-to-use/when-not/alternatives guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context that this tool surfaces native write requirements before mutation, though it omits details like rate limits or authentication 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?

It is a single efficient sentence with the prerequisite condition front-loaded. The list of resources is compressed but readable; no sentence is wasted.

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?

An output schema exists, so the description need not explain return values. For a simple read-only setup guide, it sufficiently conveys what is read and when to call it, though it could clarify the relationship between account, formats, and write requirements.

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

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

Schema description coverage is 100%, and the schema fully documents adAccountId including its numeric pattern and the LINKEDIN_ADS_ACCOUNT_IDS constraint. The description adds no parameter-level details beyond what the schema already 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 states a specific verb (Read) and concrete resources (account, supported formats, native LinkedIn write requirements), which separates it from sibling data-listing tools. It does not explicitly name sibling alternatives, but the purpose as a prerequisite setup/reference guide is clear.

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 gives a clear usage condition: call this before preparing changes. It does not state when not to use it or name alternatives, but the intended context is explicit enough to guide selection.

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

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

Annotations already declare readOnly, idempotent, and non-destructive, but the description adds real behavioral context beyond them: it enumerates the individual probes it performs and states the security guarantee that the token is never returned. It does not say what a failure looks like (error vs. a report with a failing field), which is the one relevant behavioral gap for a health check.

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 that establishes read-only scope first, then lists the checks. No filler and nothing repeated from the schema or annotations.

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?

An output schema exists, so return shape needn't be explained, and annotations carry the safety profile; the description supplies the substantive content — what is probed and the token-non-disclosure guarantee. Only the failure/partial-success semantics are left unstated, a modest gap for a diagnostic 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 100% and the single optional adAccountId is fully documented in the schema, including its default behavior. The description adds no parameter-level detail, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — a read-only LinkedIn Ads health check — and enumerates exactly what it verifies: token validity, reachable ad accounts, the reporting endpoint, and the API version header. That is clearly distinguishable from the data-retrieval siblings (get_campaigns, get_insights, list_ad_accounts) without opening any schema.

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

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

The framing as a health/diagnostic check gives a clear context for when to call it: verifying credentials and connectivity before running reports. It does not explicitly name alternatives or exclusions, even though linkedin_list_ad_accounts overlaps on the account-listing behavior.

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 provides highly valuable behavioral context beyond the annotations and schema. It specifically states the scope of data visibility (only configured accounts) and dictates the default handling of test accounts ('Test accounts are excluded unless asked for').

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 definition is highly concise and structured. The first sentence defines the core function, followed immediately by constraints and default behaviors, ensuring zero 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?

The definition is exceptionally complete. It clarifies the source of the data, the returned fields, and the specific default handling of exceptions (test accounts). Nothing necessary for a correct invocation is omitted.

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 100% schema coverage, the baseline is high. However, the description adds vital operational context that the schema lacks, specifically mentioning the source list ('LINKEDIN_ADS_ACCOUNT_IDS') and the exact subset of data returned, thus adding meaningful 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?

The description clearly identifies the action ('List'), the resource ('LinkedIn sponsored ad accounts'), and specific data points returned ('currency, status and serving status'). It establishes a very clear operational scope.

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 doesn't name competing tools, it defines the operational boundaries: 'Accounts outside the configured list are never returned.' This acts as a strong usage guideline by setting expectations on scope and data availability.

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 this is a read-only, idempotent, open-world, non-destructive call. The description adds real value on top: it says the result pairs creatives with actual ad names, splits landing URLs from media URLs, and explicitly excludes delivery metrics. A note on pagination via pageToken/coverage would have made it a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each earning its place: what it lists, how it structures URLs, and what it deliberately omits. The key scope statement is front-loaded and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full annotation coverage, the description need only frame scope and exclusions, which it does. The remaining gap is sibling disambiguation against linkedin_get_creatives and linkedin_list_media, which matters in a tool family this dense.

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 adIds, limit, pageToken, and adAccountId are all fully documented in the schema, including the maxItems of 10 and the account allowlist requirement. The description adds no parameter-level detail (such as the adIds exact-resolve mode versus paging), so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (list) and resource (images and playable videos used by ads of an account), plus the notable detail that ad names are included and landing URLs are separated from media URLs. It does not explicitly distinguish itself from the sibling linkedin_get_creatives or linkedin_list_media, which an agent could easily confuse it with.

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 exclusion 'Does not report delivery' implicitly routes delivery questions to linkedin_get_delivery_status, and 'list a page' (in the schema) implies adIds is the targeted lookup path. But there is no explicit statement of when to pick this over linkedin_get_creatives or linkedin_list_media, so the agent must infer the boundary.

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=false, so the safety profile is covered. The description adds that results include download URLs and processing status, but since an output schema exists that disclosure is partly redundant, and it says nothing about permission requirements or pagination behavior beyond what the schema notes.

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 dense sentence, front-loaded with the verb and resource, ending with the disambiguating exclusion. No wasted clauses.

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 a full output schema, complete parameter docs and safety annotations, the definition covers nearly everything needed to call it. The one residual gap is explicit guidance on which sibling to use for ad performance data instead.

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%, including the images/videos enum and paging semantics, so the schema carries parameter meaning. The description adds only the notion of an 'account' library scope; baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List account image/video library files') plus what the results carry (download URLs, native processing status), and explicitly excludes the adjacent concern ('not ad performance'). An agent can separate it from linkedin_get_media, linkedin_get_creatives and linkedin_get_insights without opening a schema.

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

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

The trailing 'not ad performance' clause gives a clear negative steer toward the insights/statistics siblings, and 'library files' implies a browse/enumerate context. However, it never names the alternative tool to use when performance data is actually wanted, so the routing is implied rather than 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds the behavioral trait that multiple pivots are crossed in a single request, but says nothing about rate limits, async behavior, or the fact that results come from a statistics engine. With annotations doing heavy lifting, this is adequate but 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?

Two tight sentences with zero waste; the core capability (multi-pivot reporting) is front-loaded before the differentiating detail. Nothing is redundant.

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 100% schema coverage, an output schema, and full annotations, the description only needs to convey the multi-pivot value proposition, which it does. It could be slightly stronger by explicitly contrasting with get_insights/get_demographics, but nothing essential for correct invocation 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 all 11 parameters are documented in the schema, including the pivots ordering semantics. The description reinforces the pivot limit ('up to three pivots') but adds no syntax or format detail beyond what the schema already provides. 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?

States a specific verb ('Run') and resource ('LinkedIn Ads report') with a concrete capability: grouping by up to three pivots. It also distinguishes itself from siblings by naming the unique cross-pivot combinations it enables, so an agent can tell it apart from get_insights or get_demographics.

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

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

The description gives a clear trigger for using it — when you need to cross pivots like campaign×device or campaign group×serving location in one request. However, it does not explicitly name the alternative tools to prefer when pivot crossing isn't needed, leaving that routing to inference.

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

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

While annotations cover safety hints (readOnlyHint), the description provides unique behavioral context regarding the output: specifically listing that it returns 'the fields that would actually be sent, the ones LinkedIn would drop, and the twenty field ceiling.'

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 highly concise and well-structured. The core function is front-loaded, and the critical operational constraint ('Makes no request to LinkedIn') is used as a powerful concluding statement.

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 definition is complete for a validation tool, covering the 'why' (reporting rules), the 'what' (pivots/metrics), the operational constraint (no API call), and the nature of the results.

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%, meaning the schema handles the vast majority of semantic definition. The description primarily restates the nature of the inputs (pivot/metric) rather than adding unique semantic meaning beyond the schema's constraints.

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 uses a specific verb ('Check') and resource ('pivot and metric combination') and immediately distinguishes its purpose: validating against LinkedIn reporting rules before using other tools.

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 provides clear usage context by advising the user to run it 'before spending a call on it' and explicitly states that it makes 'no request to LinkedIn,' implying its use as a pre-flight safety check against fetch tools.

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