Customer.io MCP by usefulapi

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

The readOnlyHint annotation already establishes this as a safe read, so the description's burden is lighter. It adds the underlying REST mapping (GET /v1/campaigns/{campaign_id}), which is modestly useful, but says nothing about auth, not-found/error behavior, 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 short sentences with zero filler, and the core action is front-loaded ahead of the endpoint detail. 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 one-parameter read tool with full schema coverage and no output schema, the description covers what an agent needs to invoke it. It could optionally note what the campaign payload contains or that the id must exist, which keeps it short of 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% for the single campaign_id parameter, so the schema already documents it. 'By id' in the description adds no syntax, format, or accepted-type detail beyond what the schema provides, so the baseline 3 applies.

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

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

The description states a specific verb and resource ('Get a single campaign by id'), and 'single' implicitly contrasts with the sibling customerio_list_campaigns. It does not explicitly name that sibling as an alternative, so it stops short of a full 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: retrieving 'a single campaign by id' suggests the lookup case versus listing, but there is no explicit when-to-use statement, no named alternative (e.g., customerio_get_campaign_metrics or list_campaigns), and no prerequisites mentioned.

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, so safety is covered. The description adds the underlying REST endpoint (GET /v1/campaigns/{campaign_id}/metrics), which is genuinely useful for a REST-backed tool, but it omits any rate-limit, pagination, or empty-result behavior. With annotations carrying the safety profile, a 3 is appropriate.

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 the purpose front-loaded and no filler. The endpoint sentence is defensible as a disambiguator for a REST-backed API, though it is the one part that could be trimmed without losing capability 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?

For a read-only, single-required-parameter tool with a fully documented schema and no output schema, the description covers what the tool returns at a conceptual level (delivery/engagement metrics over time) and how to reach it. Only the absence of any discovery path to campaign_id keeps it from being fully 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 description coverage is 100%, so the schema already documents type, steps, period, and campaign_id in full, making 3 the baseline. The phrase 'over time' loosely corroborates the period/steps bucketing semantics but adds no format or default detail beyond what the schema states.

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 ('Get delivery/engagement metrics for a campaign') plus the scope ('over time'), so the agent can distinguish it from customerio_get_campaign, which retrieves campaign configuration rather than performance data. It stops short of naming any sibling explicitly, so it lands at 4 rather than 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?

The purpose implies when it applies (you want metrics, not campaign metadata), but there is no explicit when-to-use, no prerequisite conditions, and no mention of alternatives such as customerio_list_campaigns for discovering campaign ids. Usage is inferable but not guided.

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, so the safe-read profile is covered by structured data. The description adds the underlying REST mapping (GET /v1/customers/{customer_id}/attributes), which is modest extra context, but says nothing about behavior when the identifier is missing, unknown, or ambiguous across cio_id/email.

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 clauses, zero filler, with the purpose front-loaded and the API mapping trailing. Nothing here needs trimming.

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

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

For a single-parameter read tool with no output schema, the description plus annotations cover what an agent needs to invoke it. It would be stronger if it briefly noted the return shape (attribute key/value map) or the not-found behavior, but nothing essential 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?

With only one parameter and 100% schema description coverage, the schema already documents customer_id and its accepted identifier forms. The description's '(profile fields)' wording adds a little vocabulary but no syntax or format detail 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?

The description states a specific verb and resource ('Get a single person's attributes'), clarified by the parenthetical '(profile fields)', which clearly separates it from siblings dealing with messages, segments, or campaigns. It does not explicitly name a sibling, but the resource boundary is unambiguous.

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: fetch profile fields for one known person. There is no when-to-use vs when-not guidance, nor any pointer to the alternative (e.g., customerio_search_customers) when the identifier is unknown. The 'single person' phrasing is the only selection cue.

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 readOnlyHint annotation already establishes this is a safe, non-mutating read. The description adds useful framing that 'messages' means delivery records and pins the exact REST endpoint, but says nothing about pagination behavior, result ordering, or rate limits. With annotations carrying the safety profile, 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 short sentences, zero filler, with the resource and scope front-loaded and the endpoint reference trailing. Nothing could be removed without losing 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?

For a simple read-only list tool with three fully documented parameters and no output schema, the description covers purpose, scope, and endpoint. The only gap is return-shape and pagination semantics, which are partly handled by the 'start' cursor description in the schema.

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

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

Schema description coverage is 100%, so the schema already documents customer_id, limit, and start with their meaning. The description adds no parameter-level detail beyond what is in the schema, which is the expected baseline when the schema does the work.

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 messages (deliveries)') plus a clear scope qualifier ('sent to a single person') and even names the underlying API endpoint. The scope qualifier cleanly separates it from the sibling customerio_list_messages, which lacks the single-person constraint.

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 by the phrase 'sent to a single person', which tells the agent this requires a customer_id and returns only that person's history. However, it never explicitly states when to prefer this over customerio_list_messages or what happens with pagination across calls.

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, so the safety profile is covered. The description adds the underlying API route (GET /v1/customers/{customer_id}/segments), which is modestly useful context, but says nothing about pagination, result ordering, or what happens when the customer has no segments.

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, zero waste, with the scope statement front-loaded ahead of the endpoint detail. Nothing is padded or repeated.

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-only lookup with no output schema, the description plus annotations give enough to call it correctly. The endpoint reference is a nice touch, though it omits any note on return shape or multiplicity, which is the only remaining 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 coverage is 100% for the single parameter, so the schema already documents customer_id. The description reinforces that it is a single person's id but adds no format, source, or constraint beyond what the schema provides. 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 the segments a single person belongs to.' The phrase 'a single person belongs to' implicitly scopes it to one customer, which helps distinguish it from the sibling customerio_list_segments. It does not name that sibling explicitly, so it stops short of full 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?

Usage is implied by the scope ('a single person belongs to'), steering an agent that already has a customer_id, but there is no explicit when-to-use, when-not, or naming of the alternative list_segments. Adequate but leaves the agent to infer routing against a very large sibling set.

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 supplies the underlying endpoint (GET /v1/campaigns), which mirrors structured data rather than adding behavioral context. With readOnlyHint already covering the safety profile, the description should add things like pagination behavior, result caps, or rate limits, none of which appear.

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, front-loaded sentences with no filler; the scope statement leads and the endpoint reference follows. Nothing needs to be trimmed for an agent to act on it.

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 trivial zero-param read tool this is close to adequate, but with no output schema the description does not indicate what a campaign record contains or whether results are paginated. A brief note on return shape would make it complete.

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

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

The tool takes zero parameters, so the baseline of 4 applies. There is nothing for the description to clarify beyond the already-complete empty 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 ("List all campaigns in the workspace"), which is unambiguously distinct from the singular customerio_get_campaign. It does not, however, explicitly differentiate itself from sibling list/get tools such as customerio_get_campaign_metrics, so it stops 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?

There is no guidance on when to choose this over customerio_get_campaign (single campaign) or customerio_get_campaign_metrics. The scope word "all" hints at bulk retrieval, but no condition, prerequisite, or exclusion is 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?

The readOnlyHint annotation already tells the agent this is a safe read. The description adds only the underlying API route (GET /v1/collections), which is marginal context for the agent and does not cover pagination, result size, or return shape for a listing operation.

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 purpose. The second sentence (API endpoint) is marginal, but it is terse and does not crowd out the primary 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?

For a zero-parameter list tool with annotations and no output schema, the essentials are covered, but critical list-tool behavior such as whether results are paginated or capped is unstated. That omission keeps it at minimum-viable rather than complete.

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

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

The tool takes zero parameters and the schema is empty, so there is nothing for the description to clarify. Baseline 4 applies for a no-parameter tool.

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') plus a precisely scoped resource ('reusable data collections in the workspace'), which is unambiguous. It does not explicitly differentiate itself from siblings, but none of the listed siblings (campaigns, segments, exports, messages) covers collections, so confusion risk is low.

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 statement of when to call this tool, what prerequisite state is needed, or what alternative to prefer. Usage is only inferable from the name and the word 'List'; the description provides no guidance at all.

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?

readOnlyHint=true already covers the safety profile, so the bar is lower. The description usefully names the underlying endpoint (GET /v1/exports), hinting at the App API surface, but says nothing about pagination, result ordering, or export status filtering for a list operation.

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 with the resource stated first and the API mapping second; nothing is wasted and the key information is front-loaded.

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

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

For a zero-parameter list tool with no output schema, the description should ideally say what is returned (export records, fields, pagination behavior). It names the endpoint but leaves the return contract entirely unspecified.

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

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

The tool takes zero parameters, so the baseline of 4 applies. There are no parameter semantics the description could 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?

States a specific verb (List) and resource (data exports) scoped to the workspace. It is unambiguous against siblings like list_campaigns or list_segments, though it does not explicitly contrast itself with any alternative.

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

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

The description says what the tool does but gives no guidance on when to use it, no prerequisites, and no mention of alternatives or related operations. An agent gets no routing help beyond the verb.

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?

readOnlyHint=true already tells the agent this is a safe read. The description adds useful context beyond that: it returns only *sent* messages, is workspace-scoped, and maps to the App API endpoint GET /v1/messages. It does not address pagination behavior or the (slightly inconsistent) presence of a drafts filter alongside a 'sent messages' scope.

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 with the scope and filters front-loaded and the API endpoint tacked on compactly. No wasted wording.

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 list tool with full schema coverage, the definition covers scope, filters, and endpoint adequately. There is no output schema, and the description says nothing about the shape of returned message objects or pagination via the `next` cursor, which is a minor remaining 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 100%, so all six parameters are already documented in the schema. The description only summarizes the filters at a high level (type/campaign/newsletter) and omits drafts, limit, and the start cursor, adding essentially nothing over 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+resource (list sent messages/deliveries) and scope (across the workspace), which implicitly separates it from the sibling customerio_get_customer_messages. It never names an alternative tool explicitly, so it stops short of full sibling 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?

The mention of workspace-wide listing and type/campaign/newsletter filters implies when the tool is appropriate, but there is no explicit when-to-use guidance or exclusion against the per-customer sibling customerio_get_customer_messages. Usage 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?

readOnlyHint=true already tells the agent this is a safe, non-mutating read, so the safety burden is covered by annotations. The description adds useful disclosure of the response shape (id + name + type) and the underlying endpoint, but says nothing about pagination, ordering, or result size 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 compact clauses: the purpose first, then returned fields and endpoint. No filler, no redundancy, everything front-loaded.

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

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

With no output schema, the description usefully discloses the returned fields, which is the main thing an agent needs for a zero-parameter list tool. It stops short of covering pagination or result-volume behavior, but the essentials are present.

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

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

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. Nothing in the description conflicts with the empty 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 (List) and resource (segments), scoped to the workspace, and enumerates the returned fields (id + name + type). It distinguishes itself implicitly from the narrower customerio_get_customer_segments by saying 'all segments in the workspace', but 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?

The phrase 'all segments in the workspace' implies this is the workspace-wide enumeration rather than a per-customer lookup, which is the natural contrast with customerio_get_customer_segments. However, no when-to-use condition, prerequisite, or alternative is stated outright.

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, so safety is covered. The description adds useful context that this read is executed as POST /v1/customers, but it says nothing about result volume, pagination continuation behavior, or rate limits, so it only modestly exceeds what the annotations provide.

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

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

Three short, front-loaded sentences: what it does, the filter shape with a concrete example, and the underlying endpoint. Every element earns its place with no redundancy.

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

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

For a filtered search with a readOnly annotation and no output schema, the definition conveys the filter contract well. It omits what the response contains (list of people plus a next cursor), which is a minor gap given no output schema is present to cover it.

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 itself already documents limit, start (cursor from a previous response's next), and the filter object with the same example shape used in the description. The description largely restates schema content, 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 and resource ('Search/list people') plus the scoping mechanism (a Customer.io filter with segment or attribute conditions), which separates it from sibling list/get tools returning campaigns, messages, or segments. It does not explicitly name or rule out a sibling, so it falls just short of 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 implied through filter examples ('filter={"segment":{"id":7}}'), which tell the agent the tool is for conditional lookups, but there is no explicit when-to-use or when-not guidance, nor any pointer to alternatives like get_customer_attributes or list_segments for non-filtered retrieval.

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 destructiveHint=true, so the safety bar is lower; the description reinforces this with the real-email warning and immediate-delivery note, and adds the API endpoint (POST /v1/send/email). It stops short of mentioning rate limits, idempotency, or that unsubscribed recipients are skipped unless overridden.

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 critical warning front-loaded before purpose and endpoint. No filler or restatement of the title.

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 9-parameter mutation tool with nested objects and no output schema, the description covers the destructive nature and delivery target but omits preconditions (template setup), default unsubscribe-skipping behavior, and override interactions. Adequate but with clear gaps.

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 schema fully documents all 9 parameters; baseline 3 applies. The description adds only that the `to` recipient is the delivery target and that a template is referenced, without clarifying identifiers vs message_data usage.

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 ('Send a transactional email using a transactional message template') plus delivery semantics ('delivers immediately to the `to` recipient'). It does not explicitly differentiate from the sibling customerio_trigger_broadcast, which an agent could plausibly confuse with this tool.

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?

'⚠️ SENDS A REAL EMAIL' implies caution but gives no explicit when-to-use/when-not-to guidance or routing versus trigger_broadcast. The precondition that a transactional_message_id must already exist is left implicit.

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 only declare destructiveHint=true; the description adds the materially important fact that delivery goes to real recipients and identifies the underlying endpoints (POST /v1/send/broadcast via /v1/campaigns/{broadcast_id}/triggers), which explains the side effect beyond the annotation. It still doesn't say whether triggering is idempotent, throttled, or how long delivery takes.

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, warning front-loaded, no filler. The endpoint reference is compact and placed after the risk statement so it never delays the critical warning.

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 mutation tool with no output schema, the definition covers risk, resource, and endpoint, which is enough to call it correctly. A brief note on what is returned (trigger id) or on asynchronous delivery would close the remaining 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 100%, so the schema already explains broadcast_id, recipients override, data Liquid variables, and the three ignore/duplicate flags. The description adds no parameter-level meaning beyond that, 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 ('Trigger an API-triggered broadcast') plus the delivery scope ('resolved recipient set'), which cleanly separates it from transactional-send siblings. It does not explicitly name the alternative tool (customerio_send_transactional_email), so the differentiation is implicit 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 leading '⚠️ SENDS TO REAL RECIPIENTS' gives a clear condition for caution and tells the agent this is a live-production operation, not a dry run. It stops short of naming when to prefer customerio_send_transactional_email or what prerequisites (e.g. broadcast must already exist) must hold.

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