MCP GSC AI Agent Carrier Class Fleet

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

With no annotations supplied, the description carries the full burden, and it is exceptionally transparent: it discloses that answers are served byte-for-byte from GSC's record, that no model is in the answer path, that sig is a keyring signature over {id, a, ts} verifiable at the registry URL, and that prev affects ranking only. The 'Not investment advice' caveat adds an additional behavioral boundary.

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 dense but not bloated; each sentence contributes either scope, return-shape, or usage caveat. It could be slightly trimmed, but it earns its length by covering authenticity, signature verification, and context semantics in a compact form.

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 there is no output schema and no annotations, the description fully explains what the tool returns (answer object fields, shelf, suggested links, sig), how the signature can be verified, and how prev changes behavior. Nothing essential for invoking 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?

Schema description coverage is 100%, so q and prev are already fully documented in the input schema. The description's mention of prev as 'one-turn context' largely restates the schema's own description ('one-turn context, ranking only') and adds no new parameter-level meaning 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 ('Ask GSC's AI assistant elyssah') and defines the exact topical scope (GSC, AI Agents for Beauty & Personal Care, records, investment market). It is clearly distinct from the sibling fleet/carrier/jurisdiction tools, so an agent can identify it without opening the schema.

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

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

The description gives clear context for when to use it: for natural-language questions about GSC and the listed topics, with the prev parameter for one-turn context. It does not explicitly name alternative tools or say when not to use it, but no sibling tool offers the same Q&A role, so the guidance is adequate.

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 no annotations, the description carries the behavioral burden. It does disclose a useful behavior: the tool prefers a resident sovereign endpoint and falls back to the fleet root covering the member's region. It also hints at evolving availability ('as they go live'). However, it does not mention output shape, error behavior, or side-effect 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?

The description is short and front-loaded, but the second sentence is vague and fails to earn its place. The first sentence conveys the core lookup behavior; the second mostly obscures it with jargon.

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 tool with no annotations and no output schema, the description is incomplete. It leaves out return value structure, example inputs, failure modes, and clear differentiation from sibling resolution tools. The cryptic terminology increases the chance an agent will misuse or underuse the tool.

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

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

Schema description coverage is 100%, so the baseline is 3. The description lightly reinforces that 'node' is a member code used to find the serving surface, and 'category' relates to sovereign Carrier answers, but it does not add meaningful syntax or format 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?

The description indicates that a member code resolves to a 'serving surface' or endpoint, and the title says 'Find Carriers for a jurisdiction,' so the general purpose is discernible. However, the phrasing is domain-specific and metaphorical ('serving surface,' 'sovereign Carrier set'), and it does not clearly distinguish this from sibling tools like resolve_carrier or get_fleet.

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 explicit guidance is given for when to use find_carriers versus alternatives such as resolve_carrier or list_fleets. The second sentence mentions category and capability addressing but does not provide actionable selection criteria or exclusions.

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

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

No annotations exist, so the description must fully disclose behavior. It fails to indicate side effects, authentication needs, or what the tool actually does when called.

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

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

The description is very concise (one sentence), but it sacrifices clarity. It could be restructured to separate the core concept from the contextual note about buyer-side compute.

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 zero parameters, no output schema, and no annotations, the description must be highly informative. It is not; the agent remains uncertain about the return value or how to use the 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?

The tool has zero parameters, so the description is not required to add parameter meaning. Baseline is high, and the description adds no confusion here.

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 is cryptic and jargon-heavy, mentioning 'Carrier AI Agent class' and 'sell-side positioning' without clearly stating what the tool returns. It does not effectively distinguish from siblings like 'get_fleet' or 'resolve_carrier'.

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 is provided on when to use this tool versus alternatives. Sibling tools like 'find_carriers' and 'get_fleet' exist but no differentiation is made.

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 are not provided, so the description carries the burden. It discloses the tool is read-only implicitly (returns a full record), but doesn't state whether it's a read operation, potential errors, or network implications. There's no destructive or write implication, but the description doesn't explicitly confirm safety. It adds field context (what the record contains) beyond the schema, which is useful.

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

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

The description is a single concise sentence that is front-loaded with the core purpose and then enumerates the fields. There is no waste, and it efficiently summarizes the returned record. However, it could be slightly more structured with a colon or bullet list, but the current form is acceptable.

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 (one parameter, no output schema, no nested objects), the description is quite complete. It tells the agent what the tool returns (fields are listed) and which fleet to specify. The absence of an output schema is mitigated by listing the fields. Missing details like authentication or errors are not critical for such a straightforward read 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 description coverage is 100% (the single parameter 'fleet' is documented with an enum and description). The description does not add any new meaning about the parameter beyond what the schema provides. Baseline 3 is appropriate because the schema already covers the parameter fully.

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 returns the full record for one fleet, with a specific list of fields (root, region, slot range, index, catalog, Card URL pattern). It distinguishes from sibling list_fleets (which lists fleets) and get_fleet_stats (which provides stats), though it doesn't explicitly name them. The verb 'Get' and resource 'one fleet' are clear.

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

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

The description implies when to use this tool: when you need the full record for a single fleet, as opposed to listing fleets or getting stats. However, it doesn't provide explicit when-not conditions or alternative tool names. There's no mention of prerequisites or use cases beyond that.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It does communicate that monthly transaction volume is not returned here and that the given numbers are canonical, which is useful. However, it does not explicitly state that the operation is read-only, what the return format is, or whether the numbers are live/refreshed.

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

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

The description is compact and front-loaded with the headline canonical number. The second sentence adds a valuable boundary about where monthly transaction volume lives, though the precise breakdown figures are mildly data-heavy for a tool description.

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

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

For a zero-parameter tool with no annotations and no output schema, the description is mostly sufficient: it names the key stats and points elsewhere for transaction volume. It falls short by not explicitly saying 'returns' and by not clarifying how this tool relates to get_fleet and list_fleets, which an agent might reasonably confuse it with.

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 input schema has zero parameters and schema description coverage is 100%, so there is no parameter documentation burden on the description. The description appropriately adds no parameter details.

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

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

The description clearly identifies the resource as canonical fleet statistics, giving concrete figures for live AI agents, carriers, AIO agents, and jurisdictions. However, it never states a verb like 'returns' or 'provides,' and it does not explicitly distinguish itself from sibling tools such as get_fleet or list_fleets.

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

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

There is no explicit guidance about when to use this tool versus alternatives like list_fleets, get_fleet, or find_carriers. The note about monthly transaction volume living at an external URL is a boundary, but it does not convey when or when not to select this tool.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. However, it does not mention whether the tool is read-only, what it returns, or any side effects. The description is misleading as it suggests a verification process rather than a data retrieval function.

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

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

The description is a single sentence but it is not concise for a tool description: it reads like a tutorial on how to perform verification rather than a compact summary of the tool's functionality. It is verbose and poorly 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 no parameters, no output schema, no annotations, and 9 sibling tools, the description fails to explain what the tool does, what it returns, or how to use it. An agent would be unable to determine the tool's purpose or 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 input schema has zero parameters, so schema description coverage is 100%. There is no need for parameter information in the description, and a baseline of 4 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 talks about 'how to verify a GSC surface's residency claim' which is instructional rather than stating what the tool does. It does not clearly indicate that the tool returns a residency receipt, and it fails to distinguish from sibling tools like get_fleet or resolve_carrier.

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 is provided on when to use this tool versus alternatives. The description is a how-to guide, not a usage guideline, and does not mention any context or prerequisites.

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?

No annotations are provided. The description does not disclose behavioral traits such as whether the tool is read-only, idempotent, or has side effects. For a tool with zero parameters, the burden is lower, but the absence of any behavioral context is a gap.

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

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

The description is a single, front-loaded sentence that conveys the essential information without unnecessary words. It is appropriately sized for the tool's simplicity.

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 description explains what the tool provides (surface and endpoint for each purpose) but does not specify the format of the output (e.g., list, mapping, text). For a tool with no parameters and no output schema, more detail about return structure would improve completeness.

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

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

The input schema has no parameters, so schema description coverage is 100%. The description does not need to add parameter meaning, and the baseline score of 4 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 that the tool provides the GSC surface and endpoint for data, discovery, transaction, and standards. It uses specific resource terms ('GSC surface', 'endpoint') and distinguishes from siblings, which focus on carriers, fleets, and jurisdictions.

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 implies usage when an agent needs to know which surface to use or the endpoint for a given purpose, but it does not provide explicit guidance on when to use versus alternatives, nor does it mention any prerequisites or exclusions.

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

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

No annotations are provided, so the description must carry behavioral disclosure. It does convey what data the tool surfaces — the three fleet roots, associated regions, slot ranges, entry points, and headline agent counts. However, it never explicitly states that this is a read-only listing, nor does it mention freshness, pagination, or any operational caveats.

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 first sentence is concise and informative. The second sentence is a dense, promotional jumble of numbers and program names that adds questionable value for an agent deciding how to call the tool. Some structure would help, but the overall description is still short.

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 parameterless list tool, the description covers the main content of the result: the three fleet roots with regions, slot ranges, and entry points. However, it does not specify the response structure, and the headline statistics are ambiguously presented, leaving some uncertainty about what exactly the tool returns and in what format.

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 input schema has zero parameters, and schema description coverage is 100%, so there are no parameter semantics for the description to clarify. This matches the baseline for a parameterless tool: no additional parameter documentation is needed.

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 the three live fleet roots (Global, APAC, LATAM) and their regions, slot ranges, and entry points. It uses a specific verb and resource, and the title reinforces this. It does not explicitly distinguish itself from the sibling 'get_fleet', but the plural 'fleets' and the enumerated roots make the scope reasonably clear.

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

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

The description gives no explicit guidance on when to use list_fleets versus alternatives like get_fleet or get_fleet_stats. Usage is only implied by the phrase 'live fleet roots.' There are no conditions, exclusions, or mentions of related tools, so an agent gets little help choosing this over a more specific fleet tool.

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

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

There are no annotations, so the description must carry the behavioral burden. It describes the data content but does not disclose operation characteristics such as whether this is a read-only listing, whether the list is static or dynamic, or what the exact response format is.

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 short and front-loaded with the essential content: what is listed and what each entry contains. The final sentence is slightly stylistic but still conveys that this map is the authoritative source for residency claims.

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

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

For a zero-parameter tool, this is mostly adequate: it identifies the returned content and scope. However, without an output schema or usage guidance, an agent is left to guess the exact return structure and when to choose this tool over resolve_jurisdiction.

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 input schema has zero parameters, so the baseline of 4 applies. No parameter documentation is needed, and the description adds no parameter semantics because there are none to describe.

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 that the tool returns the eighteen jurisdictions where GSC Carriers are resident, along with each jurisdiction's serving Azure region. It is distinct in scope from sibling tools like resolve_jurisdiction, though it relies on the tool name for the explicit 'list' verb.

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 is given about when to use this tool versus alternatives like resolve_jurisdiction or find_carriers. The line 'Residency is the checkable claim' hints at a use case, but it does not explicitly state when to call this tool or when to prefer a sibling.

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses that the slot is validated against the fleet's real range and that the result is canonical, with the Card as source of truth. It does not mention error handling or side effects, but the read-only resolver behavior is reasonably transparent.

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 arrow expression front-loads the core contract in one compact line, and the second sentence adds just enough behavioral context. There is no fluff or repetition of schema details.

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

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

For a simple two-parameter resolver with no output schema, the description specifies the output, the validation behavior, and the trust model. It could be more complete by naming sibling alternatives and describing what happens on validation failure, but the core calling context is 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. The description adds meaning by explaining that the slot is validated against the fleet's real range, which goes beyond the schema's regex pattern, and by clarifying the relationship between fleet, slot, and the resulting URL.

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 the exact function: it maps a fleet and slot to the canonical Card URL. The word 'canonical' and the line about the Card being the source of truth distinguish this resolver from sibling tools like find_carriers and get_carrier_doctrine.

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

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

The description gives clear operational context—after resolving, fetch the Card to confirm the Carrier—but does not explicitly state when to choose this tool over alternatives or when not to use it. Usage is implied rather than spelled out.

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 no annotations, the description carries the behavioral disclosure burden. It clearly communicates a read-like lookup by mapping a code to output fields, which implies no side effects, but it does not explicitly state read-only behavior, error handling, or what happens for unknown member codes. This is adequate for a simple resolver but not fully transparent.

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

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

The description is a single, compact sentence that conveys the input and three outputs with no wasted words. The essential information is front-loaded in the input-to-output mapping.

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

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

For a single-parameter, low-complexity tool, the description is largely complete: it names the input and the key output categories. There is no output schema and no mention of error behavior, but the agent can still determine how to invoke the tool 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 description coverage is 100%, and the schema already documents the single 'code' parameter with format guidance ('Member code, e.g. CH') and maxLength. The description adds no additional meaning beyond restating that the input is a member code, so it meets the baseline without enriching parameter 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 states a clear input-to-output mapping: 'Member code → residency status, serving endpoint, and Azure region.' This identifies the resource and result, and the title 'Resolve one jurisdiction' reinforces the singular scope. It does not explicitly name or contrast sibling tools like list_jurisdictions or resolve_carrier, so differentiation is mostly implicit.

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 arrow phrasing implies use when you have a member code and need residency status, serving endpoint, and Azure region. However, there is no explicit guidance about when to choose this over siblings like list_jurisdictions or get_residency_receipt, nor any exclusions or alternative routing.

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