AI Web Research & Research Brief Agent

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

Beyond the annotations (destructive=false reading is already covered by destructiveHint=true and idempotentHint=true), the description discloses the no-effect status list, that the response carries updated run details, and — critically — that a valid x402 payment signature is required in _meta["x402/payment"]. The payment/auth prerequisite is a major behavioral fact not derivable from structured fields.

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

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

Front-loads the core action and the no-op conditions, then groups usage, examples, and payment requirements cleanly. Slight waste in the two near-identical usage examples, which convey essentially the same invocation.

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?

An output schema exists so return values need not be spelled out, and the annotations already cover the destructive/idempotent profile; the description still adds the x402 payment requirement and the status no-op rule. Minor remaining gap: what happens to partially produced run results after abort is not stated.

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

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

Schema description coverage is 100%, so both runId and gracefully are already documented in the schema, and the description adds no syntax, format, or default details for either. The example 'Gracefully abort run' hints at the gracefully flag but does not explain its semantics 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 (Abort) and resource (Actor run) plus the qualifying state ('currently starting or running') and the inverse state where it is a no-op. An agent immediately knows what the call does and when it will have any effect, 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?

Provides an explicit when-to-use rule ('stop a run that is taking too long or misconfigured') and an explicit when-it-does-nothing list (SUCCEEDED, FAILED, ABORTING, ABORTED, TIMED-OUT). Two usage examples show concrete invocations, so routing is unambiguous.

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/idempotent/non-destructive, so the safety profile is covered. The description adds material context beyond that: an x402 payment signature is required in _meta, and waitSecs blocks up to a 45s cap. It doesn't describe rate limits or failure modes of the payment path, so not a 5.

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

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

Front-loads the purpose, then organizes USAGE, examples, and the payment caveat into labeled blocks with no filler. The two example user_inputs are mildly redundant with the USAGE section, keeping it from a 5.

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?

An output schema exists, yet the description usefully previews the result shape (summary as past-tense, nextStep as prescribed follow-up) and surfaces the payment prerequisite. An agent has everything needed to call it correctly; minor gaps only in error/payment-failure behavior.

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 both parameters are documented in the schema itself (runId and waitSecs with range, default, cap). The description largely restates the waitSecs semantics rather than adding new meaning, so the baseline 3 applies.

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

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

States a specific verb and resource ('Get detailed information about a specific Actor run') and describes the returned payload. It is clearly distinguishable from siblings like abort-actor-run (different verb) and get-dataset-items (different resource).

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

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

Gives explicit context ('Use to check the status of a run started by any Actor-running tool') and a clear rule for the blocking behavior ('Pass waitSecs > 0 to block until terminal'). It does not name when NOT to use it or an alternative status-checking path, so it stops short of a full when/when-not treatment.

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

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

Annotations already cover the read-only/idempotent/non-destructive profile, so the description's added value is the payment requirement ('requires an x402 payment... include a valid x402 payment signature in _meta') plus the default limit of 20 and the clean=true shortcut semantics. The payment/auth disclosure is meaningful context annotations cannot express, though return/pagination behavior is left unstated.

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

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

Front-loaded with the core purpose and scope, followed by trigger condition, examples, and payment notice. The USAGE/EXAMPLE blocks are somewhat verbose but each line carries usable information; no wasted restatement of 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?

An output schema exists so return values need not be explained, and the key operational extras (payment protocol requirement, default pagination, clean flag) are present. Missing only explicit guidance on alternatives/non-use cases for a fully documented multi-param read tool.

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

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

Schema description coverage is 100%, so all eight parameters are already documented in the input schema. The description only echoes limit default and clean semantics, adding no syntax or format detail beyond the schema, which matches the baseline 3 when the schema does the heavy lifting.

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

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

States a specific verb and resource ('get items (rows) from a dataset') and explicitly scopes it against adjacent capabilities: 'Returns the rows themselves, not dataset metadata, counts, or a schema.' An agent can distinguish this from metadata/count-style tools 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?

Gives a clear trigger condition ('When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly') plus two concrete usage examples. It does not name an alternative sibling or state when NOT to use it, so it stops short of the top tier.

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?

Beyond the annotations (readOnly/idempotent/non-destructive), it discloses two non-obvious behaviors: the response preserves the original Content-Encoding, and the call requires an x402 payment signature in _meta["x402/payment"]. Payment/auth requirements and response-encoding caveats are exactly the context annotations cannot convey.

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

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

Front-loaded with the core purpose and scoping constraint, then payment requirements last. The USAGE line partially restates the opening paragraph and the examples are somewhat boilerplate, but nothing is bloated or buried.

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

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

With a rich annotation set, full schema coverage, and an output schema (so return values need no explanation), the description supplies everything remaining an agent needs: exact-key requirement, encoding behavior, and the x402 payment prerequisite.

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 both parameters (recordKey, keyValueStoreId) are already documented in the schema. The description only adds the 'requires the exact key name' constraint, which is marginal extra meaning — the baseline 3 applies when the schema does the heavy lifting.

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

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

The first sentence states a specific verb (get), resource (value/record in a key-value store), and explicitly scopes it as a single record rather than a key listing. An agent can classify the tool 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?

"Use when you need to retrieve a specific record (JSON, text, or binary) from a store" gives clear triggering context, and the 'not a listing of all keys' clause rules out a competing interpretation. It stops short of naming a concrete alternative tool or explicit when-not conditions, so it is not a 5.

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

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

With annotations already declaring openWorldHint and destructiveHint, the description still adds material behavior: it requires an x402 payment, costs $1.99 per completed brief, and specifies the exact metadata key (_meta["x402/payment"]) plus the client-support prerequisite. That is real operational disclosure beyond the structured annotations. It stops short of describing failure modes or the wait/poll tradeoff (which the schema covers).

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 short sentences, each carrying load: purpose, price, and the payment prerequisite with its exact key. Slight boilerplate in the opening 'This tool calls the Actor...' sentence, but no padding or 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?

An output schema exists, so return values need no explanation, and the schema also handles wait behavior and polling guidance. The description covers the one thing structured fields cannot: the mandatory payment flow and its cost. Only the absence of any usage/routing guidance keeps it from being 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 100%, so the schema fully documents research_question, context, requirements, and waitSecs, including defaults and the fire-and-forget option. The description adds no parameter-level syntax or semantics beyond that, so 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 names the concrete action (calls the Actor and retrieves its output) and the embedded Actor description pins down the actual purpose: 'Cited multi-source web research and synthesis,' i.e. producing a source-backed research brief. The first sentence is somewhat tautological since the Actor name equals the tool name, but the appended Actor description rescues the purpose. Siblings are unrelated run/dataset utilities, so differentiation is implicit.

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

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

The description gives no when-to-use vs when-not guidance and names no alternative tool. The only usage steer ('use a specific question that needs web research...') lives in the input schema, not the description. An agent gets pricing context but no routing logic.

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