Agent Outposts

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

With no annotations, the description carries the full burden and does well: it discloses that this is a read of a pre-verified document, that each intent carries a verification date, and that no auth or cost is involved. It omits error behavior for unknown brands and any caching/freshness guarantees beyond the embedded date.

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 core payload description is front-loaded and earns its place, but the 42-slug brand list is duplicated verbatim from the schema, roughly doubling length with zero added information. Trimming that block would make this a tight, high-signal definition.

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

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

For a one-parameter read tool with no output schema, the description is nearly self-sufficient: it defines the returned fields and their possible values so the agent knows what it will get. Only the absence of sibling routing and error semantics keeps it from full marks.

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 'brand' parameter already documents every valid slug, so the description adds no new parameter meaning — it restates the same enumeration. 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?

Precise verb+resource: 'Get one brand's door-state document from its Outpost', and it enumerates exactly what the document contains (five intents, four state values, sanctioned route, evidence source, verification date). It never names the sibling list_outposts, so an agent must infer the single-brand vs. list distinction on its own.

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

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

Usage is only implied by the enumerated brand slugs and the 'Free, no API key' note — there is no explicit statement of when to call this versus list_outposts or register_intent, and no guidance on what happens for an unlisted brand. Adequate but leaves routing to inference.

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

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

With no annotations, the description carries the full burden and does meaningful work: it discloses cost/auth ('Free, no API key') and the non-obvious semantics of industry_leader entries (doors verified open, no intent registered there), which prevents misreading the results. It stops short of describing result ordering, size, or whether the network list changes over time.

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 resource and its definition before the status caveat and the cost note. The nested parentheticals ('an Outpost (a demand registry for brands with no agent door of their own)') are dense, but every clause contributes definitional content an agent would otherwise have to guess.

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

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

For a zero-parameter list tool with no output schema, the description covers the key return semantics: brands plus per-Outpost status, and the special meaning of industry_leader. The absence of any mention of the response shape or how outposts map to the sibling tools keeps it just short of fully self-contained.

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?

Zero parameters, so the baseline applies; nothing about arguments needs explaining. The description correctly implies an unfiltered full-network listing with no arguments required.

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

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

States a specific verb ('List') and resource ('Agent Outposts network') and defines the domain term inline: brands with an Outpost, a demand registry for brands with no agent door of their own. The industry_leader status is explained concretely with examples (peetscoffee, kroger, bestbuy), so the agent knows exactly what this returns 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?

Usage is implied rather than stated: an agent can infer this is the discovery/enumeration tool for outposts, distinct from get_outpost_door_state or register_intent. But no sentence says when to prefer it over those siblings, and there are no explicit 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?

With no annotations, the description carries the burden and does substantial work: it enumerates the return payload, discloses the v1 caveat that "changed" is false until a re-census bumps the version, and states "Free, no API key." Missing are polling cadence, token expiry, and any error behavior, which matter for a poll-style operation.

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

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

Three sentences, front-loaded with purpose, then return fields (necessary since there is no output schema), then the v1 caveat and cost. The middle sentence is a long comma-laden enumeration but every clause carries information the agent would otherwise lack.

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

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

For a two-parameter, no-output-schema tool, the description covers return values, the census-static limitation, and access cost, which is most of what an agent needs. It omits polling frequency expectations, token lifetime, and failure modes, leaving a modest gap for an operation that is inherently repeated.

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 both parameters are already documented, including a full brand enum list and the token's origin. The description only re-states that the token comes from the intent receipt, adding no format, validation, or scoping detail 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 ("Poll a notify token from an intent receipt for door-state changes at a brand's Outpost") and ties it to the registration artifact produced by register_intent, which separates it from the direct-read sibling get_outpost_door_state. An agent can tell what this tool does and what input lineage it expects 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 prerequisite is explicit: the token comes from an intent receipt, so usage follows register_intent, and the "changed since your registration" field telegraphs the wait-for-change use case. It does not explicitly contrast with get_outpost_door_state or say when a direct state read is preferable, so it stops short of full routing 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?

With no annotations, the description carries the full burden and does so: it discloses persistence semantics, the exact receipt contents, the two status values (intent_recorded vs demand_logged) and their condition, the failure mode (recording_unavailable, no ticket issued), a concrete rate gate (100/caller/day, 5,000 service-wide), no auth requirement, and a secrecy warning for the poll URL.

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?

About 200 words, but front-loaded with the core action and receipt contract, and every clause (rate gate, privacy warning, open-door no-op) adds operationally useful information. The Industry Leader exception is the one piece that arguably belongs earlier, since it changes whether the call does anything at all.

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 7-parameter mutation tool with no output schema and no annotations, the description fully compensates: it enumerates the return payload, the status values, the error path, rate limits, and the no-op case. An agent has everything needed to decide whether to call and how to interpret the result.

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

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

Schema coverage is 100%, so the schema already documents all seven parameters including enumerations and lengths. The description adds only light context — that the notify registration is how you learn about re-census changes and that the intent joins the brand-visible aggregate — without explaining parameter formats or interactions 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?

Specific verb + resource ('Register intent at a brand's Outpost: declare what you came to do') with the key precondition stated up front — the brand's door is walled for that intent. It also distinguishes this from pre-check tools by describing the walled-door case and noting that at Industry Leaders the call records nothing and returns a door_open pointer, so an agent can tell what this call actually accomplishes.

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 context is clear: call it when the door is walled for your intent, and at Industry Leader brands (peetscoffee, kroger, bestbuy) the call is a no-op returning a door_open pointer. It stops short of explicitly telling the agent to call get_outpost_door_state or list_outposts first, leaving the pre-check routing to inference.

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