Port OS Smart Home

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

Annotations declare destructive=true and openWorld=true, and the description earns that bar by disclosing the crucial behavioral trait that 'accepted' only means dispatch succeeded, not that the physical outcome occurred. It also decodes error semantics (result_timeout = unknown outcome, MESSAGE_UNSUPPORTED/AMBIGUOUS = nothing sent, unreachable = rejected) and forbids automatic retries of state-changing commands — none of which is in 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?

Front-loaded and organized with numbered steps, but it is extremely long and carries material that duplicates the schema (waitForResult is re-explained three times) and that arguably belongs in a bundled skill — it even advertises itself as being for 'tools-only clients without resources/read.' The device-class catalogue is useful for routing but bloats the definition considerably.

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 six-parameter, open-world, destructive dispatch tool, the description covers discovery, payload construction, route selection, result semantics, failure modes and post-write verification. An output schema exists, so return values needn't be spelled out, yet the status vocabulary (accepted/responded, queue-contents fields) is explained where it affects agent behavior.

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 routing semantics beyond the schema: which command classes return correlated results and therefore need waitForResult (search, library pages, get-snapshot) versus which must omit it (playback, volume, power), plus the rule to verify with fresh endpoint_query instead. It also clarifies that payload must match the declared message and that {} is used for fieldless commands.

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?

Opens with a specific verb-plus-resource statement ('Control connected devices and services, retrieve results, capture camera snapshots') and immediately positions the tool against its siblings by directing discovery to endpoint_query/group_query and metadata changes to endpoint_manage/group_manage. An agent can tell what this tool does and what it does not do 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?

Explicitly states the precondition (discover the endpoint/group first and copy the full id, message and routeId), the when-not (do not use this to rename or change membership — use endpoint_manage/group_manage), and names alternatives throughout. It even supplies end-to-end recipes for the two hardest workflows (live music queue, lighting scenes) with per-step tool routing.

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

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

Annotations cover the safety profile (destructive=true, readOnly=false, idempotent=false), yet the description still adds substantial context they cannot: rename/type changes survive provider rediscovery, disabled endpoints stay metadata-readable but cannot receive messages, DELETE may be undone by rediscovery, and MERGE_INTO leaves the source disabled without creating an ID alias.

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?

Purpose and the operation menu are front-loaded, and nearly every sentence carries non-obvious behavior. It is a dense ~190-word block that would read faster as a per-operation list, and a couple of clauses (rediscovery mentioned twice) could be consolidated.

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 destructive, multi-operation, open-world-adjacent tool this covers preconditions, per-operation consequences, conflict behavior, and the user-confirmation step; return values are handled by the existing output schema, so nothing an agent needs to call it safely 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 83% and each parameter already carries a description, so the description only needs to add constraints. It does add the critical one ('full endpoint ID from endpoint_query') and the conditional applicability of mergeInto, name, type and enablement via the operation list, though it never maps operation values to their required parameters explicitly.

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 ('manage the names, types and registry entries of your devices and connected services') and enumerates the exact operation set. It also explicitly distinguishes itself from the sibling 'control' by declaring it never performs physical control, and points to endpoint_query for the ID.

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 explicit sequencing ('Use endpoint_query first and copy the full endpoint ID'), a decision rule for the common ambiguity (two simulator endpoints return 409; 'disable or delete the duplicate instead'), and a pre-flight requirement for the irreversible ops ('identify the actual endpoint and explain the effect to the user; never assume two endpoints are duplicates because their names match').

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/non-destructive, yet the description goes far beyond them: cache versus forced provider reads, FRESH/STALE/UNREACHABLE semantics, PROVIDER_NO_STATE, and the rule that STALE values cannot support safety claims. That is meaningful behavioral context the annotations cannot express, and it materially changes how an agent interprets results.

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

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

Front-loaded with purpose and usage, but it then expands into a long reference essay with a bulleted taxonomy of device categories and several maxims ('Names alone do not prove identity', 'Simulator state does not establish household device state') that read like documentation rather than selection guidance. Much of it earns its place given the complexity, but the volume and overlap with schema text cost 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?

An output schema exists, so return values need not be spelled out, and the description covers the remaining decision-relevant gaps: account scoping for IDs, routeId preservation, pagination, enablement defaults, and state-freshness interpretation. Nothing an agent needs in order to call this correctly is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description earns extra credit by disambiguating expand ('adds observations; it does not discover more devices or send controls') and explaining cache behavior behind forceDeviceAttributeQuery. It still restates some schema-level facts (ID-only lookups, default enablement), and the 'paginationContext.nextToken' phrasing drifts from the actual nextToken parameter, so it is strong rather than flawless.

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?

Opens with a specific verb-and-resource cluster (find devices/services, discover controls, read state) and explicitly defines what an endpoint is, including non-obvious cases like a filesystem or media library. It names the sibling tools it is not (group_query for rooms, endpoint_manage for inventory, control for commands), so an agent can route correctly 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?

Gives explicit entry guidance ('Start with a focused name, room or category query'), the known-device path ('For a known device, use endpointId'), pagination behavior, and named alternatives with the conditions that select them. It also states the default scope (enabled devices) and how to widen it, which is exactly the kind of when-to-use detail that prevents wrong 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 cover read-only/idempotent/no-destruction, yet the description adds substantive behavior: single match vs multi-match results differ, results carry cached card readings so no second call is needed, primary refreshes that card's readings, unknown card ids are rejected with the valid list, and FRESH vs STALE readings must be reported with age. These are exactly the traits an agent cannot infer from the schema.

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

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

Purpose and the 'never render a second card' rule are front-loaded, then argument guidance, then fresh/stale reporting. Every paragraph carries load, but sentences are long and multi-clause, and the primary examples block is dense enough to slow scanning.

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 an 8-parameter, nested-schema, output-schema-bearing read tool, the description covers everything that matters operationally: multi-match degradation, cached vs refreshed readings, card selection, and the UI/rendering constraint. Return values are already in the output schema, so nothing 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 baseline is 3; the description earns above that by adding decision-level meaning for primary (which card ids exist, what each is for, requires endpointId, unknown ids rejected), expand (replaces the default cached selection, short names use capability-interfaces), and the single-device requirement for query. nextToken, enablement and maxResults are left entirely to 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?

Opens with a specific verb+resource: 'Show Port OS devices with their supported controls', and clarifies it opens the device's canonical widget UI. It distinguishes itself from endpoint_query (shares the same selection/expansion/pagination arguments) and from control ('Showing a device does not start live video or send a control command'), though the query-vs-show split is implied rather than stated outright.

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 explicit operating instructions: always call this tool to show a device, never render a second card or map, pass one full endpoint ID (or a query matching one device) to get controls, otherwise you get only a name list. It maps common user intents to primary card ids via worked examples. It stops short of saying when endpoint_query is the better choice instead.

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 destructive=true and openWorld=true, but the description goes far beyond them: it discloses that native effects cannot be rolled back, that BEST_EFFORT falls back locally as PARTIALLY_APPLIED, that OUTSIDE_PRINCIPAL suppresses native attempts, and per-provider support (Hue create/delete/membership/rename, Roborock rename only, Sonos unimplemented). It also warns that deleting routes leaves them disabled and orphaned so rediscovery cannot resurrect them.

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?

Purpose and alternatives are front-loaded, but the body is a dense wall of internal status vocabulary (NOT_SUPPORTED, NOT_DECLARED, OUTSIDE_PRINCIPAL, PARTIALLY_APPLIED) and several sentences restate what the enum descriptions in the schema already say (providerSync, enablement). The information is valuable but the phrasing is spec-leak prose rather than scannable guidance, so not 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 9-variant, destructive, provider-syncing batch mutation this covers the essentials: authorization requirements, idempotency, etag/precondition handling, per-provider capability matrix, partial-failure semantics, and interpretation of result statuses. The output schema exists, so the added status guidance ('Do not report a partial save as fully synchronized') is interpretation help rather than duplication.

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 operations, etags, providerSync and idempotencyKey; baseline would be 3. The description adds cross-cutting meaning the schema does not: one starting etag shared by every reference to a group in a batch, requestId correlation over position, idempotencyKey reuse only for the identical request, and that MERGE_INTO/SET_ENABLEMENT/route enablement accept only PORTOS_ONLY.

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?

Opens with a concrete verb+resource+scope: 'Organize rooms and device groups: create, rename, change members, enable, disable, merge or delete them.' It explicitly separates itself from siblings by naming group_query for reads and control for device actions, so an agent can route 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?

States when to use it (group organization), when to use alternatives ('Use control for device actions', 'Read group IDs and etags with group_query first'), and hard prerequisites ('Obtain explicit user authorization for the exact MERGE_INTO or DELETE_GROUP targets'). It also gives the dry-run path via validateOnly and the recovery path for stale etags/idempotency reuse.

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 establish readOnly, idempotent, non-destructive behavior, and the description adds substantial operational context: pagination behavior, merged-ID redirects, controller versus message semantics, disabled-group visibility, and membershipComplete caveats. No behavior contradicts 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?

The purpose is front-loaded and the description is organized by operational concern. It is dense and lengthy, but most sentences carry useful guidance for a complex query tool, with only minor 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?

Given the tool's complexity, rich schema, annotations, and output schema, the description covers the important call patterns, caveats, and sibling handoffs. An agent has enough information to invoke group_query correctly without opening other definitions first.

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%, but the description still adds meaningful semantics beyond the schema, including that id reads one group, merged IDs report redirectedFrom, expand requires id, forceDeviceAttributeQuery refreshes observations, and enablement survives pagination. These details help an agent choose parameters correctly.

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?

Starts with a specific verb and resource list: find rooms, floors, zones, homes, and device groups, plus their members and controls. It distinguishes the tool from group_manage and control by explaining query versus management/action semantics.

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?

Explicitly says to call without arguments first to load full context, follow pagination tokens, and filter with query only when the account is large. It also routes related needs to siblings, such as endpoint_show for maps and group_manage SET_ENABLEMENT for disabled groups.

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 and idempotentHint=true, and the description restates idempotency while adding the consequential detail that a stopped monitor needs a new subscription to resume — real context beyond the annotation flags. It still says nothing about required permissions or what the cancellation response contains.

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 with no filler, lead sentence states the action and the ID sourcing rule. The middle sentence ('Select the intended subscription by name, source endpoint and catalog event; names are not cancellation keys') is slightly convoluted and could momentarily read as endorsing selection by name.

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, return values need not be explained, and the annotations already carry the destructive/idempotent profile. The description covers the ID sourcing and the irreversibility consequence, leaving only auth/permission expectations unaddressed.

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 property description already states 'Exact subscription ID returned by subscription_list. Never use a display name or endpoint ID.' The prose largely echoes that, so it adds little semantic value 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 ('cancelling one Port OS event subscription') and scopes it to a single subscription by exact ID. It also implicitly distinguishes itself from subscription_list and subscription_inspect by naming them as the ID sources rather than as the operation itself.

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?

Explicitly directs the agent to obtain the ID from subscription_list or subscription_inspect and warns that names are not cancellation keys, which is the main misuse path for a cancel tool. It does not, however, discuss when cancellation is inappropriate or what alternatives exist for temporarily pausing a monitor.

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, closed-world), and the description adds real semantics on top: the returned query is described as 'safe' (implying redaction), and it explicitly warns that a retained active subscription only proves registration, not that a client received or acted on a camera event. That caveat prevents a concrete misreading of the result and 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?

Two sentences, front-loaded with the action and resource, followed by the return contents and the one critical caveat. Nothing is redundant with the name or 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?

A one-parameter read tool with full schema coverage, explicit annotations and an output schema, so return values need not be spelled out further. The description nonetheless names what comes back and closes the main interpretive risk, leaving nothing an agent needs 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% and the single id parameter is documented in detail, including the 'never use a display name or endpoint ID' constraint. The description's 'exact ID returned by subscription_list' largely restates the schema, 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 specific verb (Inspect) and a precisely scoped resource (one Port OS event subscription, by exact ID), and names the sibling that produces that ID. An agent can separate it from subscription_list, subscription_cancel and subscription_label_edit 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 description tells the agent where the required ID comes from (subscription_list) and the schema forbids substituting a display name or endpoint ID, which rules out the main misuse. It does not contrast this tool with read-adjacent siblings such as endpoint_show, but the lookup path 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?

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false. The description adds substantive context beyond that: the event, endpoint, filter, and destination are immutable, so the mutation surface is confined to a label — useful reassurance that matches the non-destructive annotation.

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, no filler, with the scope constraint front-loaded and the escape hatch to the alternative workflow second. 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?

With rich annotations, a full input schema, and an output schema, the description covers the remaining gaps: immutability of sibling fields and the replacement workflow. Only minor details (e.g., error behavior on unknown ID) are absent, which is acceptable given the structured fields available.

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 only 50%, but the description compensates by telling the agent to use a PLAIN name-value object, which explains the nested {type: 'PLAIN', value: ...} shape that the schema alone presents without rationale. The id parameter's exactness requirement is already covered in 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 (change display name), a specific resource (one Port OS event subscription), and a precise selector (by exact ID). It is clearly distinguishable from subscription_cancel, subscription_list, and subscription_inspect, which operate on lifecycle or listing rather than the label.

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?

Explicitly scopes the tool to display-name changes only, then names the excluded case (changing what is watched) and prescribes the alternative workflow: create a replacement monitor and cancel the old ID. An agent has no ambiguity about routing.

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

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

Annotations already declare safety (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is low; the description adds real behavior by requiring the agent to exhaust every nextCursor for a complete enumeration. It also discloses a hard constraint, that these tools never accept callback URLs or signing keys, which is not in 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?

Front-loaded first sentence states what is returned; the second paragraph carries use-case and constraint information. Both paragraphs carry weight, though the mention of the monitor-creation path via events/subscribe is only tangentially related to a list 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?

With rich annotations, an output schema that covers the return shape, and a fully documented single parameter, the description fills the remaining job of telling the agent how to page and what to do next. Only the missing distinction from subscription_inspect 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% and the single cursor parameter is documented as an opaque nextCursor, so the baseline is 3. The description earns the extra point by making the pagination contract operational (follow every nextCursor) rather than merely describing the field.

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?

A specific verb (enumerate) plus resource (Port OS event subscriptions), and it names the payload fields returned: exact IDs, names, source endpoint, catalog event, status. That is enough for an agent to distinguish this list operation from subscription_inspect or subscription_cancel 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?

Gives a concrete trigger and full follow-on procedure: stopping a camera monitor means listing, following every nextCursor, selecting the intended monitor, then calling subscription_cancel with its exact ID. It also pre-empts the creation path (host's events/subscribe capability). It does not explicitly say when to prefer subscription_inspect over this list, so there is a small gap against alternatives.

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