OutageDeck

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

Annotations already cover read-only, idempotency, and destructiveness. The description adds meaningful behavior: the feed is read live before saving, must be publicly reachable, and credentials never travel through conversation. This goes beyond annotations and helps set expectations.

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, each delivering distinct value: purpose, prerequisites, and validation/security behavior. There is no filler or redundancy, making it both concise and well-structured.

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 simplicity (2 parameters, no output schema), the description covers prerequisites, validation, security, and usage exclusions. It doesn't describe the success response, but that's a minor gap given the annotations and sibling context.

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 schema already describes both parameters with 100% coverage. The description adds context that the URL should point to a Statuspage or Instatus status page and must be publicly reachable, which is helpful but not a large departure from the schema. It doesn't add significant new parameter-level detail.

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

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

The description clearly states the tool registers a vendor not tracked by OutageDeck by pointing to its Statuspage or Instatus page, with a specific outcome. This differentiates it from sibling CRUD tools like update_custom_provider and remove_custom_provider.

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

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

It provides explicit when-to-use context (for vendors OutageDeck does not track) and a when-not-to-use rule (feeds behind authentication must be set up on the account page). It also states prerequisites like API key and plan, giving clear guidance without naming alternative tools but still steering correctly.

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 and closed-world, so the safety profile is largely covered. The description adds useful non-obvious behavior: it returns a shareable status-board link and a prefilled alert setup link, which an agent could not 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?

Three tight sentences: scope first, then the decision context, then the return payload. Nothing is redundant and the most important qualifier (up to 12 providers) 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?

With no output schema, the description usefully specifies the returned artifacts (status-board link, alert setup link). It is nearly complete for a one-param read tool, though it could say more about what the 'verdict' contains when nothing is wrong.

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?

Single parameter with 100% schema description coverage, which documents the accepted slug/name/product-name forms. The description adds the 'up to 12' bound but no additional syntax or format meaning beyond the schema, so the baseline 3 applies.

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

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

States a specific verb and resource: a single verdict across up to 12 providers about whether any vendor is currently reporting a problem. The batch scope ('up to 12 providers') is a clear functional differentiator from single-vendor siblings like get_provider_status, though no sibling is named 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?

Gives clear context ('Use before debugging an integration failure to answer "is it us or them?"') and implies the pre-diagnosis moment. It stops short of naming the alternative single-provider tools or stating when not to use this batch version.

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 indicate read-only, idempotent, and non-destructive behavior. The description adds meaningful context about the returned content (current status vs. complete timeline) but does not disclose error handling, rate limits, or other behavioral traits. This is acceptable given the annotations, though richer context would be beneficial.

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 concise, using two well-structured sentences. It front-loads the action ('Retrieve the full text') and immediately clarifies scope, with no redundant words. Every sentence adds value.

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

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

The tool is simple with one parameter, a complete schema, and an output schema. The description covers the core purpose, ID source, and content types. It is complete enough for an agent to invoke correctly, though it could mention error cases or fallback behavior, but these are likely covered by the output 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?

The schema provides 100% coverage for the sole parameter 'id' with examples and expected format. The description adds a minor note that IDs come from the search tool, which is helpful but not necessary since the schema already explains the parameter. Baseline of 3 applies because 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 clearly states the tool retrieves the full text of a search result by ID, with specific detail on two types of content (provider status and incident timeline). It distinguishes itself from siblings like get_incident_details by emphasizing it works on search results and returns full text, making its purpose 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?

The description provides clear context that IDs come from the search tool, indicating this is meant to be used after a search. It does not explicitly mention alternatives or when not to use this tool, but the context is sufficient for common use cases.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered by structured data. The description adds meaningful context beyond that: it discloses what the read actually returns and frames it as the authoritative source's own statements, which signals the data's provenance and possible staleness. It does not mention error behavior, rate limits, or freshness guarantees.

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, thoroughly front-loaded: the core purpose and return contents come first, then the slug source, then the use case. Every sentence carries distinct information with no repetition of the schema or annotations.

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

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

With no output schema and only one parameter, the description carries the burden of describing return values, and it does so by naming the four categories of returned data. Coverage is strong for a read tool; only error/freshness behavior and the relationship to overlapping siblings like get_outage_report remain 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% for the single parameter, and the schema already documents the 'incident' slug with an example. The description restates its origin but adds no format, validation, or lookup rules beyond that. 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 ('full detail for one incident') and enumerates the returned content: chronological updates from the official source, matched services, severity, and resolution state. That enumeration cleanly distinguishes it from siblings like get_provider_status, list_active_incidents, and get_outage_report 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 tells the agent where the required slug comes from ('returned by list_active_incidents or get_provider_status') and gives a clear use statement ('read what the official source has actually said about an outage'). It stops short of stating when to prefer this over get_outage_report or check_my_stack, so there is no explicit exclusion guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds context about the report's scope and content (trailing window, incident breakdowns) but does not disclose additional behaviors like pagination or data freshness.

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

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

The description is two sentences, concise and front-loaded, with no filler. The first sentence lists what the report includes, and the second gives concrete use cases, every sentence earning 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?

Given the simple 1-parameter schema and strong annotations, the description is complete for an agent to understand what the tool returns and when to use it. It enumerates the report's contents, and the lack of an output schema is compensated by the descriptive listing.

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 'days' parameter, which already has a description in the schema. The tool description repeats the default and range, adding no new information beyond what the schema provides.

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

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

The description clearly states it provides a reliability summary across all tracked providers, listing specific contents like incident totals and severity breakdowns. This distinguishes it from sibling tools such as get_incident_details (specific incident) and get_provider_status (single provider).

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 explicitly tells the agent when to use it: to answer 'which vendors had outages recently?' or to compare vendor reliability. It doesn't explicitly name alternative tools for exclusions, but the context is clear and actionable.

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), yet the description goes well beyond them by explaining truncation behavior, the meaning of reportedCodes vs. notOperational, how to interpret absent codes, and that withdrawn readings omit these lists. That is exactly the kind of output-interpretation context structured fields cannot supply.

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 is front-loaded in the first sentence, followed by usage routing and then response semantics. The reportedCodes/notOperationalCodes passage is dense but each clause carries distinct interpretation rules, so it earns its space despite the density.

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

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

With no output schema, the description must explain return values and it does: overall state, impaired services, incident lists, truncation fallbacks, and code-interpretation rules. An agent has everything needed to call it and read the result correctly.

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

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

Schema coverage is 100%, so the baseline is 3; the description adds genuine value by stating the parameter accepts a slug, provider name, or product name and that product names resolve to vendors ("claude" → Anthropic), which the schema examples alone do not make clear.

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 ('Live status for one tracked provider') and names the exact payload contents (overall state, non-operational services, open incidents) plus the source (vendor's official status feed). This clearly distinguishes it from siblings like get_uptime, get_outage_report, and list_active_incidents.

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 positions it as the triage entry point: 'Use this first for any "is X down?" question,' and clarifies accepted identifier forms. It does not name the sibling tools to use afterwards (e.g., incident details, outage report), so routing guidance stops short of full when/when-not coverage.

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), so the bar is lower, and the description adds real substance: it discloses the data source and the three distinct computations (share of time free of major outages, strict uptime counting partial outages as downtime, total impaired durations). That interpretation of partial outages as downtime is behavior an agent could not infer from annotations or schema.

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

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

A single front-loaded sentence leads with the resource and scope, then adds the metric definitions without a wasted word. Dense but every clause carries information an agent needs.

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 carries the return-value burden and does so by enumerating the three uptime metrics returned. Combined with annotations covering safety and 100% parameter coverage, an agent has nearly everything needed; only the exact response shape/naming remains 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?

Schema description coverage is 100%, so both parameters are already documented in the schema, including the 7-90 day bounds and default of 30. The description repeats the window range but adds no new syntax, format guidance, or semantics for the provider slug/name/product-name resolution. 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 — an independent uptime record for one provider over a trailing window — and pins down the exact measurement basis (OutageDeck's readings of the official status source). It implicitly separates itself from snapshot siblings like get_provider_status by emphasizing a historical window, but it never names the sibling it differs from.

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

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

Usage is only implied: the trailing-window framing suggests asking for history rather than a current snapshot, and the 7-90 day range hints at bounded historical queries. There is no explicit when-to-use, when-not-to-use, or named alternative among the many siblings (get_provider_status, get_outage_report, get_incident_details).

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

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

Annotations already declare read-only and non-destructive behavior. The description adds that it returns all open incidents, orders by severity (most severe first), and supports an optional severity filter. No contradictions with annotations.

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

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

Two sentences, front-loaded with the primary function, then a practical usage cue. No filler or redundant phrases.

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 simple schema (one optional param), strong annotations, and no output schema, the description adequately conveys scope, ordering, and filtering. It could mention the return format but the current text is sufficient for most agents.

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 schema has 100% coverage for the one optional parameter (severity) with enum and description. The description restates the filter and lists values, adding minor clarity but not exceeding the schema baseline.

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

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

The description clearly states the tool lists active incidents across all tracked providers, ordered by severity. It distinguishes from siblings like get_provider_status (provider-specific) and get_incident_details (single incident) by emphasizing the whole landscape and 'currently open' scope.

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

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

It explicitly provides a use case ('What is down right now?') and clarifies it applies across the entire cloud landscape. It does not explicitly name alternatives or exclusions, but the context is clear enough to guide selection.

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

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations by specifying that the tool 'Requires an API key' and 'only ever returns that key owner's providers', which clarifies authentication and data scoping. No contradictions with 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 description is two sentences, front-loaded with the main action ('Lists the custom providers'), and every clause adds meaning: the account scope, the definition of custom providers, and the API key requirement. There is no redundancy or filler.

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

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

For a simple, parameterless listing tool, the description covers the essential information: what is listed, whose account it applies to, and the authentication requirement. There is no output schema, but the description implies a list of providers; it could potentially clarify the output structure or fields, but given the tool's simplicity and the sibling context, the description is sufficiently complete for an agent to invoke it correctly.

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

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

The tool has zero parameters, so per the instructions, the baseline is 4. The description does not need to elaborate on any input schema since the schema is empty. The description focuses on the tool's scope and output, which is appropriate for a parameterless operation.

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

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

The description clearly states the tool's function with a specific verb ('Lists'), a specific resource ('custom providers'), and a clear scope ('on the caller's own OutageDeck account'). It also distinguishes from sibling tools by clarifying that these are 'vendors they registered themselves by pointing at a status feed we do not track in the public catalog', differentiating it from search_providers or get_provider_status.

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 provides clear context on when to use the tool: when you want to see the caller's own registered custom providers, not public catalog providers. It does not explicitly name alternatives or exclusions, but the context implies that this is for user-specific data, which is sufficient guidance given the sibling tool names and the focus on 'custom' providers.

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 mark destructiveHint=true and idempotentHint=true. The description goes further by disclosing that stored incident history is also deleted and that an API key is required. These are meaningful behavioral specifics not captured in the annotations, adding transparency beyond the structured metadata.

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

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

The description is two sentences with no wasted words. It front-loads the core action, then adds two relevant consequences (history deletion and plan slot freeing), plus a clear authentication requirement. 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 simple single-parameter deletion tool with good annotations and no output schema, the description is complete. It explains what is deleted, the side effect on incident history, the plan impact, and the authentication requirement. No material gaps remain.

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 schema already covers the parameter with 100% coverage, describing 'provider' as 'The custom provider's name or id.' The description adds no additional semantic detail about the parameter beyond what the schema provides. Hence, the baseline 3 is appropriate.

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

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

The description clearly states the primary action ('Deletes one of the caller's custom providers') and the specific resource affected. It explicitly differentiates from sibling tools like add_custom_provider and update_custom_provider by focusing on deletion, and adds relevant consequences (freeing a plan slot).

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 clearly implies when to use this tool: when the caller wants to remove a custom provider. It does not explicitly name alternatives, but the sibling list provides contextual contrast. The mention of freeing a plan slot gives additional decision-relevant context, though it stops short of explicit 'use this instead of X' guidance.

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

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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds meaningful context by noting that results are citable and have stable IDs suitable for the fetch tool, and that it searches the full scope of OutageDeck data. No contradiction with 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 description is two well-structured sentences, front-loads the core purpose, and includes concrete examples and an alternative tool without any fluff. 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?

With a single parameter, a clear output schema, and annotations covering safety, the description fully equips an agent to decide when and how to invoke the tool. The sibling comparison and citable-results hint complete the picture.

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 input schema already describes the query parameter in detail with examples. The description adds some context about open-ended queries but does not materially extend parameter semantics 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?

The description clearly states the tool searches everything OutageDeck tracks, including providers and incident history, with a specific verb and resource. It also distinguishes itself from get_provider_status, a key sibling, and mentions the stable-id/fetch integration.

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?

Explicit when-to-use guidance is provided: use for open questions like 'who had outages last week' or 'find the GitHub Actions incident', and use get_provider_status when the question is only about one named vendor currently being down. This clearly differentiates from an important alternative.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context beyond these by specifying that it returns slugs and each match's current status, which is useful behavioral information. No contradiction with 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 description is two sentences with no filler. The first sentence front-loads the purpose and output; the second gives usage guidance. Every phrase 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 simple one-parameter search tool with strong annotations and no output schema, the description covers purpose, return value (slugs and status), and when to use it. Minor omissions like result ordering or pagination are not essential for this tool's context.

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 'query' parameter, and the description enriches it by explaining searchable fields (name, product name, fragment) and providing concrete examples ('postgres', 'auth', 'claude'). This adds meaning beyond the schema's generic 'names and aliases'.

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

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

The description clearly states the tool's function with a specific verb and resource: 'Find tracked providers by name, product name, or fragment.' It distinguishes itself from siblings like the generic 'search' by emphasizing it returns provider slugs for use with other tools and that it searches tracked providers specifically.

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 explicitly says when to use the tool: 'Use when a provider argument did not resolve or to discover what OutageDeck tracks.' It does not explicitly name an alternative tool or state when not to use it, but the context is clear and actionable.

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

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

With annotations present, the description goes well beyond them: it discloses the API-key requirement, the idempotent semantics of an existing alert (counts only when delivery is allowed), the refusal path with an explanation, what a successful result guarantees, and a privacy detail that other channels' destination URLs are never returned. This is exactly the extra behavioral context annotations cannot carry.

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 the action and scope, then layers on constraints in roughly priority order. It is a fairly long block of prose, but each sentence carries distinct information (auth, idempotency, failure mode, return guarantee, privacy), so little 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 one-parameter mutation with no output schema, the description covers everything an agent needs: credentials, what happens on the success path including the reported channel, the refusal path, and what is deliberately not returned. Nothing material is left to inference.

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 parameter's description already enumerates slug, name, product name, or custom provider, so the schema does the heavy lifting. The description restates the same source distinction without adding syntax, format, or ambiguity-resolution guidance beyond it.

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 ("starts sending the caller outage alerts for one provider") and scopes it to a single provider from either the tracked catalog or the caller's custom providers. That single-provider scope plus source distinction separates it cleanly from list/search siblings like search_providers and list_custom_providers.

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 explains what starting a watch entails and the conditions under which an existing vs. new alert is used, but it never names an alternative tool or says when a caller should watch a provider versus querying it with get_provider_status. Usage is implied by the verb rather than explicitly guided.

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