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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses important behavior: signed POSTs, a one-time-only whsec_ secret, a 10-endpoint cap, and duplicate-URL refusal. These are material operational facts absent from structured fields.

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

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

Three tight sentences, front-loaded with what the tool does and the critical one-time secret behavior, then the 10-endpoint and duplicate-URL constraints. 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?

For a two-parameter mutation tool with no output schema, the description covers the key return value (endpoint plus one-time signing secret), secret handling guidance, limits, and failure routing. 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%, and the schema already explains both the URL reachability constraints and each event type in detail. The description only refers to 'chosen events' without adding parameter-level information beyond the schema, so the baseline of 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 uses a specific verb and resource ('Register a webhook endpoint') and immediately states the core effect: receiving signed POSTs for chosen events. It distinguishes itself from edit_webhook by explicitly routing duplicate URLs to that sibling.

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

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

It gives explicit usage conditions: an app may have at most 10 endpoints, and adding an already-registered URL is refused with the alternative 'use edit_webhook instead.' This tells the agent both when to call it and what to do when the call would be rejected.

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 flag destructiveHint and idempotentHint, but the description adds real consequence detail: delivery stops immediately and pending deliveries are dropped. That is exactly the kind of post-conditions annotations cannot express. It stops short of stating irreversibility or auth requirements.

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

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

Two short sentences, zero filler, and the consequence of the operation is front-loaded right after the action 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 one-parameter destructive tool with no output schema, the description covers the key post-condition an agent needs. Only minor gaps remain, such as whether the deletion is permanent or what error occurs for an unknown id.

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 single parameter is 100% documented in the schema, including its UUID format and provenance ('from list_webhooks or add_webhook'). The description adds nothing 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 ('Delete a webhook endpoint'), which is unambiguous against siblings like add_webhook or edit_webhook. It does not explicitly name or contrast with those siblings, so it falls just 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 by the destructive verb; there is no explicit guidance on when to delete versus edit_webhook (e.g., to temporarily disable delivery) or any prerequisites. An agent can infer intent but receives no routing help.

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 disclose that this is a non-read-only, open-world, idempotent, non-destructive mutation. The description adds useful behavior beyond the annotations by clarifying that callers should send only changed fields and that the signing secret remains unchanged.

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 three short sentences with no filler. The main action is front-loaded, and the most important constraints are stated immediately.

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

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

For a four-parameter mutation tool with full schema descriptions and strong annotations, the description covers the operation, partial-update behavior, and signing-secret side effect. It could optionally mention return behavior or auth expectations, but nothing critical 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 coverage is 100%, so the parameter details are already well documented. The description still adds meaningful edit semantics with 'Pass only what changes,' which goes beyond the schema's field-level descriptions.

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

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

The description states a specific verb and resource: 'Change a webhook endpoint's URL, events, or enabled state.' It clearly identifies the mutable fields and distinguishes this operation from sibling webhook tools such as add, delete, list, and test.

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?

'Pass only what changes' gives explicit partial-update guidance, which is the key usage rule for this tool. It does not name alternatives or exclusions, but the edit/change framing makes the intended context clear.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description does add one genuinely useful behavioral detail not available elsewhere - that `active: false` signals zero subscribers - but no output schema exists, so the burden of describing the returned payload is only partially met.

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 core purpose front-loaded before the response-semantics detail. Nothing could be cut 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 one-parameter read tool this is close to adequate, and the `active: false` note is a real addition. However, with no output schema, the description should say more about what else is returned (other fields, error behavior for unknown channels) than a single flag semantic.

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 `channel` parameter (name, length bounds, non-whitespace pattern), so the schema does the heavy lifting. The description mentions 'one channel' but adds no format or constraint detail 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 ('Get one channel's subscriber count'), and the singular framing naturally separates it from the sibling list_channels. It doesn't explicitly name any sibling, 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?

No guidance on when to use this versus list_channels, watch_channel, or publish_event. The agent must infer from context that this is a single-channel detail lookup; there are no prerequisites or exclusions given.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral value beyond that: results are subscriber-gated rather than existence-gated, and subscriber counts are returned, which prevents an agent from misreading an empty result as a failure. No permissions, ordering, or pagination behavior is disclosed.

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 filler. The active-channel rule is front-loaded, and the second sentence pre-empts the most likely source of confusion.

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-optional-parameter read tool with no output schema, the description covers the return content (channel names plus subscriber counts) and the inclusion rule, which is most of what an agent needs. It is silent on result ordering, size limits, and whether prefix filtering is case-sensitive, leaving minor 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%, and the prefix parameter is documented in the schema with a concrete example ("presence-", "private-"). The description says nothing about filtering, so it adds no meaning beyond the schema — 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 app's active channels") and immediately narrows the scope to channels with at least one current subscriber. The exclusion clause ("channels that nobody is subscribed to are not listed, even if events were published to them") separates it cleanly from siblings like get_channel, publish_event, and watch_channel.

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 definition makes the selection condition explicit — use this when you want currently-subscribed channels — and warns that a channel you published to may legitimately be absent. It does not, however, name an alternative such as get_channel for inspecting a specific channel that isn't listed.

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 cover read-only/open-world, while the description adds real operational context: newest-first ordering, a 7-retry policy over ~9 hours, and a 7-day retention window for delivered and failed records. That retention detail directly tells an agent how far back a query can reach, which is not derivable from any structured field.

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

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

Three tight sentences: what it returns, why to use it, then lifecycle constraints. Front-loaded with the resource and ordering, with zero 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?

There is no output schema, so the description's enumeration of returned fields plus the retry/retention semantics covers exactly what an agent needs to interpret results and bound its expectations. Nothing material is missing for a 3-parameter read tool.

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

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

Schema coverage is 100%, so limit, status enum, and webhook_id are already documented in the schema. The description adds only the implicit scoping to 'one webhook endpoint' and the newest-first ordering, which is the expected baseline 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?

The description names a specific resource and scope: 'Recent deliveries to one webhook endpoint, newest first,' and enumerates the returned fields (event, payload, status, attempts, last error). It is clearly distinguishable from list_webhooks, though it never names a 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?

'Use it to check that events reach your receiver, or why they fail' gives concrete diagnostic scenarios for selecting this tool. There is no explicit when-not or named alternative, but the two use cases are unambiguous.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real context beyond that: a cap of 10 endpoints per app and the security-relevant guarantee that signing secrets are never returned, both of which affect agent 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?

Two short sentences, front-loaded with the action and return fields, then the secret/limit caveats. No filler and nothing repeated from the 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?

With no parameters, no output schema, and annotations covering the read-only profile, the description fills the remaining gap by describing the returned fields and the 10-item cap. Nothing an agent needs to invoke it correctly is missing.

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

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

This tool takes no parameters, so there is nothing for the description to disambiguate; baseline is 4. The sentence spends its words on return shape and limits rather than redundantly describing inputs.

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?

Names a specific verb and resource ('List the app's webhook endpoints') and enumerates exactly what is returned (id, URL, events, enabled flag), which lets an agent distinguish this from list_webhook_deliveries without opening a schema. It also states a hard scope limit (at most 10 per app).

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 note that secrets are never listed and that add_webhook reveals a secret once gives partial routing for a common follow-up question. However, it never says when to prefer this tool over list_webhook_deliveries or when listing is unnecessary, so the main sibling ambiguity 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?

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds non-obvious semantics the annotations cannot express: immediate fan-out to subscribers and that cache- channels persist and replay the event to future subscribers, which materially affects a publish decision.

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 sentences, no waste, front-loaded with the core action and delivery behavior; the exclusivity constraint is placed last where a caller checks it before invoking. Every sentence earns its place.

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

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

For a publish tool with no output schema, the description covers delivery, persistence/replay, and the channel selection rule, which is sufficient to call it correctly. It omits any mention of what the call returns or error behavior, but with no output schema and full annotation coverage that gap is minor.

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 baseline would be 3, but the description adds a genuine constraint absent from the schema: 'Pass exactly one of channel or channels.' The schema presents both as optional with no oneOf, so this mutual-exclusion rule is real value beyond the 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?

States a specific verb (publish) and resource (event) plus the target (Apinator channels), and describes the delivery mechanism: subscribers receive it immediately, cache- channels store and replay. This clearly distinguishes it from the read/auth siblings (list_channels, get_channel, watct_channel, sign_channel_auth).

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

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

Gives a clear operational rule ('Pass exactly one of channel or channels') and explains the delivery context that decides reach. There is no competing publish sibling to route against, so no explicit alternative/exclusion language is needed, but no when-not guidance is offered either.

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 cover the safety profile (readOnlyHint=true, openWorldHint=false). The description adds real context beyond that: it is a pure computation mirroring the auth endpoint's output, plus the presence-channel channel_data requirement. It doesn't state whether it produces side effects (it doesn't, implied by annotations) or the exact return shape, but the added behavioral context is solid.

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

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

Three tight sentences, front-loaded with the core action, then use cases, then the one conditional requirement. No wasted words.

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

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

For a no-output-schema tool, the description adequately conveys what is produced ('exactly as your auth endpoint would return it') and documents the input requirements. Only the literal return type/format is left implicit, which is a minor gap given the deterministic nature of the operation.

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 already documents all three parameters with examples. The description reinforces the presence/channel_data link, but that fact is already in the schema's parameter description, so it adds little beyond 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 precise verb and resource: compute the auth signature for a private- or presence- channel subscription. It is immediately distinguishable from all siblings (list_channels, get_channel, publish_event, watch_channel), none of which involve signing.

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

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

Gives clear when-to-use context: 'testing an auth flow or debugging a signature mismatch.' It also flags the presence-channel condition for channel_data. No explicit when-not guidance or named alternatives, but the usage intent is unambiguous.

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

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

Adds real behavior beyond annotations: exactly one event, sent synchronously, redirects not followed, no queueing or retry, distinct event type. That materially tells the agent this is a fire-once probe rather than a durable delivery. It does not cover auth/permission requirements or what an unreachable endpoint yields.

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, front-loaded with the action and the return signal, then the constraints. Every clause carries distinct information; nothing is repeated from the title or schema.

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 probe with no output schema, the description adequately explains what comes back (status and timing) and what does not happen (queueing, retries, redirect following). The only gap is failure-mode reporting when the receiver is unreachable or the webhook id is invalid.

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

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

Only one parameter, and the schema already documents it at 100% coverage including its source ('from list_webhooks or add_webhook'). The description adds no further detail about the id beyond implying the endpoint is looked up from it, 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 ('Send one signed webhook.test event to an endpoint') plus the observable result ('report the receiver's HTTP status and timing'). The clause 'real events never use this type' cleanly separates it from publish_event and the other delivery-related siblings.

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 makes the when clear: send right now, one event, no queue and no retry, synthetically marked so receivers can distinguish it. It never names the alternative (publish_event) explicitly for real traffic, so the exclusion is implied rather than routed.

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

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

Beyond the annotations, it discloses meaningful behavior: private/presence channels are signed automatically, the watcher joins as a visible presence member, and long watches emit progress every few seconds. These are non-obvious side effects an agent needs, and they do not contradict readOnlyHint/openWorldHint.

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?

Four sentences, front-loaded with what the tool does and followed by usage, side effects, and progress behavior. Every sentence carries distinct information 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?

With no output schema, the description adequately conveys the lifecycle and the presence/signing side effects, plus progress reporting. It could say more about what the collected events look like on return, but the essentials for correct invocation 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: channel_data is characterized as presence member data ('the watcher joins as a member') and the drop-versus-count behavior of max_events is reinforced. It stops short of documenting until_events 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 opens with a precise verb+resource: subscribe to a channel over WebSocket, collect events, then disconnect. It is clearly distinguished from siblings like publish_event and list_channels, and even frames the publish/watch pairing 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?

It gives concrete when-to-use cases (confirm events are flowing, inspect payload shapes, test a publish end to end) including the ordering hint 'start the watch, then publish'. It does not state when NOT to use it or name sibling alternatives for those cases, so it falls short of a 5.

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