World Resolver

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 does not disclose what 'latest' resolves to during concurrent writes, whether retrieval requires authorization for specific artifacts, whether the version number in a response is returned, or any error behavior when an artifactId does not exist. For a read tool with zero annotation coverage it is thin.

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 well-formed sentence with the operation front-loaded. It is efficient, though slightly under-elaborated for an endpoint whose parameters need explanation.

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 annotations, no output schema, and 0% schema description coverage, the description should carry far more: behavior of the default (latest), version semantics, error cases, and return shape are all absent. It is too sparse for a two-parameter retrieval tool whose parameters are undocumented elsewhere.

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 0%, so the schema documents neither parameter beyond type and range. The description only vaguely gestures at 'version' via 'immutable version' but does not explain that omitting it yields the latest, nor what artifactId format is expected. It fails to compensate for the coverage gap.

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 (retrieve) and resource (artifact) and adds scope: latest version by default or a specific immutable version. This cleanly distinguishes it from the sibling artifact_put, which is the write counterpart. An agent can route between them without opening either 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 phrase 'or a specific immutable version' implies version selection but never explicitly states the selection condition (e.g., omit 'version' for latest, supply it for a pinned version) or when to prefer one over the other. No exclusions or alternatives are named. Usage is inferable but not 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 full behavioral burden, and it does disclose the two most consequential traits: artifacts are immutable, and reusing artifactId chains versions instead of overwriting. It says nothing about required identity/permissions (agentId), content size limits (48k), or what happens on conflicting names, leaving real gaps for a mutation tool.

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

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

Two tight sentences with zero filler; the core action is front-loaded and the versioning rule follows immediately. 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?

For a 7-parameter mutation tool with 0% schema description coverage, no annotations and no output schema, the description is too thin: it omits identity requirements, size constraints, metadata/mediaType behavior and the response shape. It covers the headline semantics but not enough for an agent to invoke it confidently.

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 0% across 7 parameters, so the description must compensate. It adds real meaning for artifactId (version chaining), workId (optional linkage) and content/mediaType ('text or structured content'), but agentId, name and metadata receive no explanation anywhere.

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 (Store) and resource (text or structured content as an immutable artifact version), and the phrase 'creates the next version' makes the write-and-version semantics unambiguous. It is clearly distinguishable from the artifact_get sibling and from the work_* tools.

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 one concrete usage rule — reuse artifactId to append a new version rather than create a fresh artifact — which is genuine when-to guidance. It offers no explicit guidance on when to link a workId or when to prefer artifact_put over the other write tools (work_update, report_outcome), so 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 fully bears the burden of disclosing behavioral traits. It implies a non-destructive reporting operation but does not explain what happens behind the scenes (e.g., whether data is stored, sent, or logged), nor any side effects or requirements.

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

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

The description is a single, front-loaded sentence that efficiently conveys the core purpose. Every word contributes meaning; 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?

Given the tool's complexity (6 parameters, no output schema, no annotations), this one-sentence description is inadequate. It does not cover required fields, parameter details, or expected outcomes, leaving significant gaps for an agent to safely invoke 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 coverage is 0%, so the description must compensate. It hints at 'success' and 'agent friction' (likely agentSteps), but does not clarify the meaning of requestId, latencyMs, failureReason, or selectedServer. The parameter names are somewhat self-explanatory, but the description adds minimal value.

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: reporting whether a resolver request worked and the agent friction involved. It uses a specific verb ('report') and a clear resource ('resolver request'), which distinguishes it from sibling tools like resolve (which likely performs the request) and submit_mandate.

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 does not specify when to use this tool versus its siblings, nor does it mention any prerequisites or context. It only describes what it does, leaving the agent to infer when report_outcome should be invoked.

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 transparently describes the internal workflow: searching the Registry, actively validating candidate surfaces, falling back to live web search, and preserving capability-gap telemetry even for weak matches. This gives a meaningful view of the tool's behavior beyond just 'resolves requests', though it omits details like output format or failure modes.

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 and front-loaded with the core purpose, then explains the process and telemetry behavior in two additional sentences. Every sentence adds meaningful detail without redundancy, though it could arguably be streamlined. The structure is effective for quick 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?

The tool is moderately complex with seven parameters and no output schema, yet the description does not explain how parameters like budget, deadline, location, or categoryHint affect resolution behavior. It provides a good high-level workflow but is not complete enough for an agent to invoke the tool correctly with all relevant context – particularly expected inputs and outputs.

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 14%, and the description does not compensate for the undocumented parameters. Only 'task' is described in the schema; budget, currency, deadline, location, telemetry, and categoryHint receive no semantic explanation in either the description or the schema. The description's general mention of 'real-world capability request' vaguely implies some context but provides no concrete guidance for these six parameters.

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 tool's purpose: resolving real-world capability requests through a multi-step search process. It goes beyond the generic verb 'resolve' by specifying the MCP Registry search, validation, and web search fallback, which distinguishes it from vaguer tools. However, it does not explicitly contrast itself with sibling tools like report_outcome or submit_mandate.

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 are any 'real-world capability request' and specifies a fallback strategy ('when native coverage is weak or absent'). It does not explicitly state when not to use it or name alternative tools, so the guidance is contextually implied but not comparative.

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 burden. It does disclose one meaningful behavioral trait: that supplier contact and spending are not enabled yet, which implies the tool only records a demand without executing purchases. However, it does not mention whether the operation is a create/update, idempotency, or other side effects, leaving gaps.

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 exceptionally concise: two sentences that front-load the primary purpose and then add the key limitation. Every word earns its place, with no redundancy or unnecessary detail.

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 has 8 parameters, 2 enums, and no output schema, the description is too sparse. It doesn't explain required parameters, how authority levels affect behavior, or what the result of submission looks like. The single limitation note is valuable but insufficient for an agent to confidently 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?

With 0% schema description coverage and no parameter explanations in the description, the agent receives no semantic guidance for the 8 parameters. The description only conveys the overall purpose, not what 'task', 'authority', 'maxBudget', etc. mean or how they should be used.

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

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

The description uses the specific verb 'Record' with the resource 'high-intent demand', clearly stating the tool's function. It also adds a distinguishing constraint ('Supplier contact and spending are not enabled yet') that separates it from sibling tools like report_outcome and resolve.

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 this tool versus its siblings. It implies a high-intent demand scenario but never mentions report_outcome or resolve, nor any exclusion criteria. The only hint is the 'not enabled yet' limitation, which is not a usage directive.

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 behavioral burden, and it does disclose two important traits: the operation is atomic and it fails when the item is already owned. It does not say how failure is signaled (error vs. return value), whether a claim can be released or expires, or whether repeat calls by the same agent are idempotent.

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 atomic-claim behavior front-loaded and the failure condition immediately after. 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?

For a simple two-parameter tool with no output schema and no annotations, the description covers purpose, atomicity, and the contention failure mode. It omits what a successful claim returns (ownership token, lease, etc.) and the error shape, which matters because no output schema exists to fill that gap.

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 0%, so the description must compensate for both parameters, yet it only implies that workId is a work item and agentId is an agent. No format, identifier source, or constraint meaning (minLength/maxLength) is clarified, leaving an agent to infer everything from parameter names.

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 ('Atomically claim an open work item') with a clear actor ('for an agent'), which separates it from work_create, work_list, and work_update. It stops short of explicitly naming which sibling to use when a claim is inappropriate (e.g., resolve or work_update).

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 a selection condition in the negative ('Claims fail if another agent already owns the item'), which implies when this tool is applicable. It offers no positive guidance on when to claim versus work_update, resolve, or submit_mandate, and no prerequisites such as agent registration.

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 disclosure burden. The word "durable" hints at persistence, but there is no mention of required permissions, what happens if the same requestId is replayed, what the call returns, or how this interacts with work_claim/work_update — substantial gaps for a mutating creation tool.

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

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

Two short sentences, front-loaded with the core action and followed immediately by the usage condition. No filler or redundancy.

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

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

This is a high-complexity mutation tool with 7 parameters, 3 required, a nested metadata object, and no output schema or annotations. The description omits required parameters, return behavior, and idempotency, leaving an agent under-informed despite an accurate one-line purpose.

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?

Seven parameters with 0% schema description coverage, and the description addresses none of them. "For another agent" loosely implies agentId, but required fields (title, objective), dueAt, requestId, capability, and metadata are left entirely unexplained.

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

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

The description states a specific verb and resource ("Create a durable work item") and adds scope ("for another agent or for later continuation"). It distinguishes the creation action from sibling lifecycle tools like work_claim and work_update, though it never names them explicitly.

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

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

It gives a clear triggering condition: "Use this when useful work cannot be completed in one synchronous tool call." That is a genuine when-to-use rule, but no when-not guidance or named alternatives (e.g., doing the work inline instead) are offered.

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 burden of behavioral disclosure, and it only partially does so. "List" implies a safe read, but the description never states pagination behavior (a limit parameter with default 25 exists), ordering, or what a returned item contains — all material for a listing endpoint with zero annotation coverage.

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

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

Two short sentences, front-loaded with purpose then filters, with no redundant or filler text. 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?

For a no-annotation, no-output-schema, 4-parameter list tool, the description is adequate but incomplete: it never mentions the limit/pagination default, the valid state values, or what the result set looks like. An agent can call it, but not optimally.

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 0%, so the description must compensate, and it names three of four filters (state, capability, assignee). It omits the limit/pagination parameter entirely and does not surface the state enum values, so the coverage gap is only partially closed.

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

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

States a specific verb and resource ("List durable work items") plus the scope ("available to agents"), so an agent immediately knows this is the read/enumeration operation. It does not name any sibling (work_claim, work_update, work_create) to sharpen the distinction, but the verb+resource is 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 second sentence signals the filtering use case (state, capability, assignee), which implies when the tool is useful. However, there is no explicit when-to-use vs alternative guidance — e.g. nothing says to use work_claim to take an item instead of listing it, or when to prefer this over work_update.

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 it does disclose one real behavioral constraint: only the claiming agent owns state transitions until completion/cancellation. However, it says nothing about what happens to unspecified fields, whether metadata is merged or replaced, permission errors, or whether transitions are validated against the current state.

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

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

Two short sentences, front-loaded with the action and followed by the governing rule, with no filler. It is perhaps terse for a six-parameter mutation tool, but nothing in the text 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 mutation tool with no annotations, no output schema, six undocumented parameters, an enum state field, and a nested metadata object, the description leaves far too much unspecified. It establishes purpose and ownership but not the mechanics an agent needs to call 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?

Schema description coverage is 0% across six parameters, and the description names none of them. 'State transitions' loosely gestures at the 'state' enum and 'completion or cancellation' at two of its values, but workId, agentId, dueAt, blockedReason, and the nested metadata object are entirely unexplained in both the schema and the description.

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+resource ('Update a claimed work item') and scopes it to items already claimed, which cleanly separates it from work_claim, work_create, and work_list. It does not name those siblings explicitly, so an agent must infer the boundary from the 'claimed' qualifier.

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 phrase 'as it progresses' plus 'The claiming agent controls state transitions' implies when the tool applies and who may call it, but there is no explicit when-not guidance or named alternative. An agent can infer the intended lifecycle position but is not told what to do instead for unclaimed items.

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