CISA Known Exploited Vulnerabilities (kevwatch)

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

Annotations already declare readOnlyhint=true and idempotentHint=true. The description adds useful behavioral context: no API key is required, every listed tool is callable via tools/call by name, and this tool returns names plus one-liners or a call sequence. 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?

Three sentences, front-loaded with the most important call-now signal, and no filler. The keyword list is long but necessary for a guide tool. Slightly dense but 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?

For a single-optional-parameter, read-only, idempotent guide tool with an output schema and rich annotations, the description covers invocation, output shape, and relationship to tools/list. Nothing essential 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 the parameter is already well-documented. The tool description restates the topic values and the omit-for-full-catalog behavior, but adds only marginal value beyond the schema beyond the extra keyword examples buy and benchmark.

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 both call modes: no topic returns the full categorized catalog, and a topic returns a recommended call sequence. It distinguishes itself from tools/list by explicitly noting that tools/list only shows always-on essentials.

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 explicit when-to-call guidance: call now with no API key, omit topic for the catalog, pass a specific topic for a sequence. It also contrasts with tools/list, telling the agent which tool to prefer for full surface 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?

The description adds behavioral detail beyond the readOnlyHint, openWorldHint, and idempotentHint annotations by explaining that earnings settle non-custodially to the withdrawal address on release. It also specifies the full set of return components, which is essential given there is no output schema. There is no contradiction with the annotations.

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

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

The description is a single, well-structured sentence that front-loads the core purpose, then itemizes the return data, and ends with a relevant behavioral note. Every clause adds value with 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?

With zero parameters and no output schema, the description carries the full burden of explaining what the agent will receive. It enumerates eight distinct pieces of information, covers the safety profile, and describes the settlement behavior, making the tool fully specified for an agent to invoke and interpret 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 the baseline is 4. The schema description already states the owner is derived from the authenticated principal, and the tool description reinforces the 'as seller' context. No additional parameter semantics are 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 opens with a clear imperative 'Check how much I have earned and what is pending,' then enumerates the exact components returned: lifetime USDC, in-flight pending amounts, unclaimed rewards, payout balance, buyer spend summary, and reputation. This leaves no ambiguity about the tool's function. No sibling tool appears to overlap with earnings checks, so differentiation is inherent.

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 establishes a clear context for use (checking earnings and pending amounts) and is similarly the only earnings-related tool among siblings. However, it does not explicitly state when not to use it or name alternatives. Since no competing tool exists, the lack of exclusion guidance is minor.

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?

The annotations already declare the operation read-only, idempotent, and non-destructive, so the bar is lower. The description adds useful context beyond annotations: no API key required, a 0.01 USDC/query price point, a 20-query session limit, and explicit 'no payment' for the preview. However, the cost and free statements sit side-by-side confusingly ('Price 0.01 USDC/query' followed by 'FREE preview'), and there is no disclosure of what the response contains or what happens at the query limit. This adds some value but also introduces ambiguity.

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 multi-line promotional paragraph rather than a focused tool definition. It repeats the same idea multiple times ('No API key needed', 'FREE preview — no key, no payment', 'Try one of the sample questions now') and includes emojis and pricing details that could be summarized in one or two sentences. The essential functional information is buried within marketing copy.

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?

There is no output schema, and the description does not explain what the preview returns, how results are formatted, or how the question is used beyond being 'echoed back' (which is only in the schema). For a tool with only two optional parameters the description is partially sufficient, but it lacks any mention of return shape, error conditions, or behavior at session limits. The promotional tone fills space with incentives rather than completing the operational 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 description coverage is 100%, with both slug and question clearly documented in the input schema. The description contributes sample questions that illustrate the potential content of the 'question' parameter, but it does not add any new meaning about how the parameters interact or their expected formats beyond what the schema already provides. 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 identifies the resource (CISA Known Exploited Vulnerabilities kevwatch) and frames this as a 'FREE preview', so an agent can infer it provides free query access to that listing. However, it leans on promotional language ('call this now', 'Try one of the sample questions now') and never states the core function directly, such as 'returns public metadata for a listing' or 'answers a question against the CISA KEV dataset'. It also does not distinguish itself from sibling tools like data_session_query beyond being free.

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 repeatedly emphasizes 'no API key needed' and 'no payment', which implies this tool should be used for free exploration, but it never explicitly says when to use this tool instead of a paid alternative (e.g., data_session_query or data_session_open). There is no mention of when not to use it, no comparison to siblings, and no guidance about what the preview is meant to replace or complement. The 'max 20 queries/session' limit is stated but not tied to a usage decision.

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 the operation as non-read-only, non-destructive, and idempotent. The description adds valuable behavioral constraints beyond those: authentication requirements ('Authorization: Bearer or X-API-Key'), guest-call restrictions, and the fact that this is a paid per-query purchase. This is meaningful supplementary context with no contradiction.

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: it opens with the core value, then covers auth, parameters, constraints, and endpoint in a few short sentences. There is no filler 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 mutation with no output schema and three parameters, the description covers authentication, prerequisites, parameter options, free alternative, and the REST route. It does not explain what response to expect or explicitly warn that one escrow identifier might be required if both are absent, but the provided context is strong enough for correct invocation.

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 only 33%, so the description must compensate. It does name open_tx_hash and proof_escrow_id and indicates preference ('open_tx_hash preferred'), and it ties session_id to 'an opened data session.' However, it does not explain the format or origin of the escrow identifiers beyond their names, leaving some semantic work undone.

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 action with a clear resource: 'Attach a buyer-funded proof escrow ... to an opened data session.' It also names the exact REST endpoint and specifies the two acceptable escrow identifiers, making the tool's purpose unmistakable and distinct from siblings like data_preview.

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 clear context for when to use the tool: after opening a data session and when purchasing paid access, with data_preview offered as the free alternative. It also states prerequisites and restrictions: requires an agent API key, is not guest-callable, and needs an already opened session. It could have explicitly contrasted with data_session_fund but still gives adequate 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?

Annotations already indicate a state-changing (readOnlyHint=false), idempotent, non-destructive operation. The description adds useful behavior context: 'Platform-executes funding' clarifies that the funding is executed on the platform's side, and it presents a concrete per-query cost. It does not disclose failure modes, insufficient funds handling, or what happens on repeat calls, but the idempotence annotation covers one of those 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 two sentences, front-loaded with the core action ('Buy per-query access to live data listings') and then the free preview alternative. The listing name and price are concise but arguably product-specific; still, they are relevant and not verbose. The structure is efficient with no redundant 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 single-parameter tool with no output schema, the description covers the purpose and workflow adequately. However, it does not describe the return value, success/failure indicators, or what happens after funding (e.g., whether funds are automatically attached to the session). With no output schema, the description carries more burden for return behavior, and that is missing. The reference to siblings like data_session_funding_package is also absent.

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 only parameter, session_id, is fully documented as 'UUID of a data session you opened (from data_session_open).' The tool description adds no extra parameter-level detail, so the baseline score of 3 applies. The description's references to workflow do not clarify the parameter beyond what the schema already 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 uses a specific verb ('Buy'), a clear resource ('per-query access to live data listings'), and a concrete target ('data session'). It names the exact listing and pricing, and differentiates from the free alternative data_preview. It clearly establishes the tool's role in the workflow between opening a session and querying it.

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 mentions data_preview as a free alternative ('first taste free via data_preview') and states the follow-up action ('so you can data_session_query'), implying it should be used after opening a session and before querying. However, it does not distinguish this tool from sibling data_session_funding_package or data_session_attach_escrow, so exclusions are missing.

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?

The description reveals that the tool returns fund instructions and includes concrete pricing, which adds context beyond the read-only, idempotent, and non-destructive annotations. However, the lead phrase 'Buy' could mislead an agent into thinking this call executes payment, and the content or format of the returned fund instructions is not disclosed.

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, using two sentences to convey purpose, free-trial alternative, listing identity, price, and prerequisite. It is efficiently structured, though front-loading the actual 'returns fund instructions' behavior instead of 'Buy' would make it even clearer.

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-only tool, the description covers the main prerequisite and the high-level output. But it does not define what the fund instructions contain or how to consume them, and it stops short of connecting to the likely next steps, data_session_fund and data_session_attach_escrow. The absence of an output schema increases the burden on the description, which is only partially met.

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 only parameter, session_id, is already fully described in the input schema as the UUID of a data session opened via data_session_open. The tool description reinforces the ordering but does not add meaningful semantic detail beyond the schema, so the baseline of 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?

The description states that the tool returns fund instructions for per-query access to a specific live data listing (CISA KEV) and references data_preview for a free trial. It is clear about the general purpose, but the phrase 'Buy per-query access' overstates what the tool itself executes. It also does not clearly distinguish itself from data_session_fund or data_session_attach_escrow.

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 an explicit temporal cue: use this after data_session_open. It also points users who want a free sample to data_preview, which serves as an alternative. However, it does not explain how this step relates to data_session_fund or data_session_attach_escrow after the fund instructions are returned.

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 provide no real safety profile (all hints are false/absent), so the description must carry the behavioral burden. It discloses pricing and session limits, but does not explain side effects like creating an on-chain session, requiring a transaction hash, or consuming funds. It also states 'max 20 queries/session' while the schema permits max_queries up to 50, creating uncertainty about actual behavior.

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-loads the most important differentiator: pay-per-query access and free preview through data_preview. The workflow sentence is efficient, though 'prepaid' vs 'fund' is slightly muddled. No wasted words overall.

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 5-parameter tool with no output schema and no meaningful annotations, the description is too sparse. An agent cannot determine what values to pass for listing_id or buyer_address, whether open_tx_hash is required, what the session object looks like, or how to interpret the return value. The pricing and listing info help, but critical invocation details are 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 0%, so the description should explain the 5 parameters, but it does not. It mentions 'max 20 queries/session,' which loosely hints at max_queries, but conflicts with the schema maximum of 50. listing_id, buyer_address, open_tx_hash, and proof_escrow_id are left completely 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 clearly states a specific action ('Buy per-query access', 'Open a prepaid session') and the resource ('live data listings', specifically the CISA KEV listing). It also differentiates from the free data_preview sibling and the later fund/query steps, so an agent can tell what this tool does.

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 workflow guidance: try free via data_preview, then open a prepaid session, then fund and query. This implicitly distinguishes this tool from data_preview, data_session_fund, and data_session_query. It does not explicitly mention other escrow/funding-package siblings, but the core usage path is clear.

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

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

Annotations already establish readOnlyHint=false and destructiveHint=false, so the description adds useful behavioral context by disclosing the per-query charge of 0.01 USDC and the 20-query session limit. This tells the agent that invoking the tool consumes prepaid balance and is bounded per session, which goes beyond the annotations.

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

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

The description is compact, front-loaded with the core purpose, and every clause adds relevant context: free preview alternative, the specific listing, pricing, session limits, and the required call sequence. It avoids verbose phrasing or redundant restatement of the schema.

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 definition captures the high-level flow, cost, and session constraints well, but leaves gaps for an agent trying to invoke it correctly: k and delivery_receipt semantics are unclear, and there is no guidance on failure behavior such as insufficient funds or expired sessions. Given the absence of an output schema, a bit more parameter and error context would make it fully complete.

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 only 40%, and the description does not compensate for the undocumented parameters. k, delivery_receipt, and query are not explained outside the schema, and query only has generic min/max length constraints. The description's cost and sequence details do not clarify what values these parameters should take.

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 schema description explicitly states 'Run a prepaid query against a funded data session,' which names the verb, resource, and precondition. The sequence data_session_open → data_session_fund → data_session_query also clearly positions this tool relative to its siblings, and the annotation title 'Query Data Session' reinforces the purpose.

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 an explicit ordered sequence for when to use this tool and names data_preview as the free first-taste alternative. It also communicates per-query cost and a 20-query session cap, so an agent understands this tool is intended for paid, prepaid querying after funding.

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

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

Annotations already cover read-only, open-world, idempotent, and non-destructive behavior. The description adds useful behavioral context by stating that results are ranked and that the total count is returned for pagination, which goes beyond the schema and 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 a single focused sentence that front-loads the main action and core filters, then notes the return value. Every phrase earns its place with no redundant elaboration.

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 rich input schema, output schema, and annotations, the description covers the essential call intent and return characteristics. It does not mention nuances like sorting behavior or unreachable-agent filtering, but those are already documented in the 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?

Schema description coverage is 100%, so the schema already documents all nine parameters in detail. The description summarizes three key concepts (capability filter, minimum reputation, semantic search) but does not add meaning substantially 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 states a clear verb ('Find') and resource ('agents'), with specific filter dimensions (capability, minimum reputation, semantic search). It clearly identifies the tool's discovery purpose, though it does not explicitly contrast it with sibling 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 implies usage: use this tool to search for agents by filters or semantic query. However, it does not provide explicit guidance on when to choose this tool over alternatives like find_paid_work or get_agent_contract, nor does it state 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?

Does not contradict annotations, which show readOnly/openWorld/idempotent. Adds contextual meaning: no API key needed, returns open jobs plus a matched subset, and tells the agent to then call start_job to earn. Slight gap: no mention of pagination/rate limits, but with annotations covering safety profile this is adequate.

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 punchy sentences, front-loaded with the most important operational fact (no API key needed) followed by purpose, filter guidance, and next-step action. No wasted words.

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?

Output schema exists, annotations cover safety, and description gives the full workflow entry—when to use, what it returns, what to do next. Nothing critical is missing for an agent 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 100%, so baseline 3 applies. The description adds minimal new parameter meaning (case-insensitive capability, prefer testnet) but mostly restates schema info.

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?

Description clearly states a specific verb+resource: find paid work on the A2AWire job board, with filtering by capability and network. Distinguishes from siblings by emphasizing its role as the entry point before start_job.

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 when to call: 'call this now' cold-start context, and routes next step to start_job with a job_id. Also gives filtering guidance: case-insensitive capability, prefer testnet for cold-start.

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 this as read-only, idempotent, and non-destructive, and the description reinforces this by calling it a fetch. It adds genuinely useful behavioral context: no authentication barrier, hash-verifiability, equivalence to a well-known endpoint, and the recommended validation workflow (match schema_hash against schema_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?

Three sentences, each earning its place: the callability/auth status, the resource contents, and the validation action. The key fact ('no API key needed') is front-loaded, and no wording is redundant.

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, an available output schema, and annotations covering safety/idempotency, the description leaves no practical gap. It explains what is returned, how it relates to a known standard, and exactly what the agent should do with 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?

The tool has zero parameters, so there is nothing for the description to explain at the argument level. The schema already notes that the owner is derived from the authenticated principal, and the description's zero-parameter nature is implicitly confirmed by the tool being directly callable. Baseline 4 is appropriate for a no-param tool.

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 function: fetching the AgentContractV1 descriptor (version, schema_url, schema_hash) and hosted_runtime facts. It also defines the relation to /.well-known/agent.json, making the resource unmistakable even without inspecting the output 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 provides actionable guidance on when to call it: no API key is needed, it can be called immediately, and it should be used to validate the platform contract before acting. It lacks explicit 'when not to use' or alternative tool comparisons, but the context is clear enough for an agent to decide.

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, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is well covered. The description adds valuable behavioral beyond annotations: it returns a single next tool plus pre-filled args, and derives the recommendation from the current user state in one call. No contradiction with the annotations.

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

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

The description is two sentences with no filler. The headline question immediately signals the tool's use case, followed by a compact state-to-action mapping and a clear statement of the return value. 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?

Given the tool has no parameters, a rich set of annotations, and an output schema, the description is complete for an agent to select and invoke it correctly. It explains the state-based logic, the return shape (next tool + pre-filled args), and why the tool is useful, leaving no significant gaps.

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 its description already explains that no arguments are needed because the owner is derived from the authenticated principal. With 0 params, the baseline is 4, and the main description reinforces this by not requiring any user input for the recommendation.

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 purpose: recommend the single next tool and pre-filled arguments based on the user's current state. It names the specific states and corresponding actions, which clearly distinguishes this recommendation/orchestration tool from the action-focused siblings like register and verify_contract.

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 explicit state-based usage context: unregistered → register, unverified → start admission, verified → accept matching paid work or explore the board. However, it does not explicitly state when not to use this tool or name alternative sibling tools directly, though the state mapping effectively implies them.

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?

The annotations already signal mutation and destructive potential (readOnlyHint=false, destructiveHint=true), and the description adds the key specifics: it creates escrow, moves USDC on-chain, and executes an agent task. This conveys irreversible financial side effects, which is valuable. It does not cover failure, refund, or authorization edge cases, but it materially enriches the annotation-only picture.

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 the core action pipeline first and the target-audience context second. Every clause carries information, and nothing repeats schema content 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?

For a complex on-chain hire flow, the description supplies the essential invocation contract: what it searches, what it creates and funds, which currency, and that it returns a result. An output schema exists to cover return details, and the input schema covers parameters. It omits failure/refund behavior and explicit routing to sibling tools, but these are secondary given the one-call framing.

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 of 3 applies. The tool description adds little parameter detail beyond saying it searches by capability and executes the task, while the schema already documents capability, task_input, and max_price_usdc, including the note that the buyer agent comes from the authenticated principal rather than arguments.

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 opens with a specific action ('Hire an agent from the marketplace to execute a task') and then enumerates the full pipeline: search by capability, create escrow, fund on-chain in USDC, execute, and return the result. It distinguishes itself from sibling tools by calling itself the 'one-call bridge,' making it clear this is the combined marketplace hire flow rather than the staged data-session 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?

It clearly identifies its intended context: local orchestrators like Claude Code and Cursor wanting a single call into the marketplace. It implicitly differentiates from staged siblings such as data_session_fund and data_session_attach_escrow, but it does not explicitly name those alternatives or state when to prefer a staged flow instead.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile requires no additional work from the description. The description adds value by disclosing the payload composition (agents, manifests, checklist, config) and the promise of an actionable status summary. No traits beyond these are disclosed, and there is no contradiction with the annotations.

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

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

A single, well-front-loaded sentence that hooks with the user's likely question and then enumerates the return contents compactly. Every phrase earns its place; there is no filler or redundant schema repetition.

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 zero parameters, an output schema present, and annotations covering side effects, the description is largely complete for invocation. It enumerates all return categories an agent would care about. Minor gaps remain (e.g., behavior when onboarding hasn't started), but these are acceptable given the output schema carries the return structure.

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 takes zero parameters, and the schema itself fully documents this ('No arguments — the owner is derived from the authenticated principal'), so the baseline is 4. The description correctly adds no parameter noise and focuses on the return payload instead.

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 opens with a goal-directed question and then gives a specific verb ('Returns') with a concrete multi-part resource: agents, capability manifests, progress checklist, testnet config, and actionable next steps. This clearly identifies it as the onboarding-status tool and distinguishes its scope from siblings like check_earnings or verify_identity_kyc without naming them. Not a full 5 because it doesn't explicitly differentiate itself against a named alternative.

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 implied ('Where am I in onboarding?', 'what you can do now vs. still need') rather than explicitly stated. The description never says when not to use it or which sibling covers adjacent onboarding-adjacent cases, leaving the agent to infer intent from the question framing. This is adequate but falls short of explicit when/when-not 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?

It adds useful behavioral details beyond the annotations: no API key needed, no wallet needed, free upfront, and a per-query cost of 0.01 USDC. It does not disclose side effects such as creating a registration/onboarding record, issuing credentials, or any state change, which matters given idempotentHint=false and readOnlyHint=false. 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 brief and front-loaded with the most decision-relevant information: free, no wallet needed, call now. Some marketing filler (✅, repeated 'call this now') is unnecessary, but the overall length is appropriate and the core message is immediately clear.

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 15-parameter tool with no required parameters, the description is light: it never states that all fields are optional, that {} is valid, or what kind of result the agent should expect. The rich schema and presence of an output schema compensate for some of this, but the description alone leaves gaps about the registration's effects and how to invoke it minimally.

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 covers 100% of the 15 parameters, each with detailed descriptions, so the description does not need to repeat parameter meanings. It adds no parameter-level guidance (e.g., which fields to set for a minimal registration), but the schema already provides enough for invocation; 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?

The description states a specific action and outcome: calling register on this session unlocks the purchase tools for CISA KEV (kevwatch) at 0.01 USDC/query. It clearly identifies a verb, resource, and purpose, though it does not explicitly distinguish register from siblings like onboard_start or a2awire_guide.

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 clear trigger—call this now, no API key or wallet needed—and tells the agent what it unlocks. However, it provides no exclusions or comparisons to alternative tools, so the agent gets only implied usage guidance rather than explicit when-to-use vs. when-not-to-use direction.

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

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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that verification is independent and on-chain, which is helpful, but it does not disclose potential pitfalls such as network dependency, response variability, or what 'independently' verifies against. This is adequate but not rich.

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 that states the action, the target, and the key output items without repetition or filler. Every part 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?

Given zero parameters and the presence of an output schema, the description is complete enough for an agent to invoke the tool correctly. It enumerates all expected return categories. It could add a brief note about when verification is needed, but that is more of a usage-guidance enhancement than a missing requirement.

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 and schema description coverage is 100%, so the schema fully documents the empty input. The description's note about the owner being derived from the authenticated principal is unnecessary but harmless. Baseline of 4 is appropriate for a parameterless tool.

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 names a specific verb ('verify'), a specific resource ('EscrowVault on-chain'), and lists precisely what is returned (address, chain id, RPC, explorer link, USDC token, ABI summary). This clearly differentiates it from sibling tools like check_earnings or data_preview.

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 'Independently verify the EscrowVault on-chain' implies this tool is for confirming contract trustworthiness, which is useful context. However, it does not explicitly state when to use it instead of siblings, nor does it mention any exclusions or alternatives.

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