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

Beyond the readOnly/idempotent/openWorld annotations, it discloses the commercial barrier (Pro key or x402 at $0.01 per call), that the server will not pay on the caller's behalf, and that a keyless call degrades into an explanation of what is required rather than a result. It also reassures that the URL argument triggers no fetch of the target host.

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 fact inventory is front-loaded and every listed item maps to an actual output field, with payment terms placed last where they belong. The opening sentence is long and list-heavy, but no clause is 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 no output schema present, the description carries the return-value burden and mostly discharges it by enumerating the facts returned, and it covers auth/payment and the keyless fallback. It does not say how multiple matching listings are shaped or paginated, which is a modest residual gap for a four-parameter, nested-object 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 100%, so the baseline would be 3, but the description adds a real constraint not encoded in the schema: 'Give exactly one of agent, wallet or url' — the schema declares no properties as required and has no oneOf/anyOf, so this XOR rule is unique value. The chain/agent exclusion is repeated from the schema rather than added.

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 enumerates exactly what is returned — first-seen date, recorded ownership changes, revoked-rating share, wallet-registered listing count, evidence level — so the vague name 'check' is fully disambiguated. It never names a sibling (search_agents, get_agent, get_agent_history), so the agent must infer that this is the trust/forensics read rather than a profile lookup.

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?

'Dated facts to read before you pay or rely on an agent, a wallet or an endpoint' gives a clear situational trigger, and 'Facts only: there is no score and no verdict' pre-empts the wrong expectation. It stops short of routing language against the sibling tools, so the agent gets context but no explicit alternative selection rule.

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, idempotent, open-world and non-destructive behavior, so the bar is lower. The description nonetheless adds real value beyond them: it discloses provenance/freshness ('Every answer says when it was read and where from') and that owner statements are attributed as the owner's own words rather than presented as fact.

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 resource, then the returned fields, then the framing caveat. The long first sentence is dense but every clause names a distinct piece of returned data; the two short trailing sentences are efficient. Little waste.

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 output schema, the description carries the burden of explaining returns and does so by enumerating the record's fields plus read-time and source metadata. Combined with a fully documented input schema, an agent has enough to invoke and interpret the tool; only the relationship to sibling tools is left implicit.

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

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

Schema description coverage is 100% and all three parameters (including both enums) are documented in the schema, including the conditional Solana-only 'registry' behavior. The description adds no parameter-level detail, 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?

Names a specific verb and resource ('What Nooscape has on record about one agent') and enumerates the concrete contents of the record (first/last seen, registrar, evidence level, shared-wallet count, registry activity, ratings, owner claims). The 'one agent' framing and 'Not a review and not a verdict' separate it from a search or an evaluative tool, though no sibling is named 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?

'Not a review and not a verdict' implies an exclusion (use a review/verdict tool such as check instead), but the alternative is never named and no positive when-to-use condition is stated. Usage is only inferable from the singular 'one agent' framing.

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 readOnly=true, idempotent=true, destructive=false, and openWorld=true, so the safety profile is covered. The description adds genuinely new context: the API key requirement and the env var name, plus the shape of what comes back (dated registry events and claims). It does not discuss pagination or result limits.

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: the data returned is front-loaded, the auth prerequisite follows. No filler, and every clause carries information.

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 read-only tool with full schema coverage and no output schema, the description covers the data content and the auth hurdle, which is what an agent needs to call it successfully. Minor gaps are pagination/volume expectations for a presumably long history.

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% – id, chain, and registry all carry their own descriptions, including the Solana-only caveat for registry. The description adds no parameter-level detail beyond that, 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?

Names a specific resource and scope: one agent's registry events (mint, transfers, profile link updates) plus the public claim history, each dated. This clearly separates it from get_agent or search_agents in spirit, though it never names those siblings 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?

Usage is implied by the word 'history' and by the enumerated event types, and the auth requirement is stated, but there is no explicit when-to-use/when-not guidance or pointer to get_agent/search_agents as alternatives.

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 readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: a hard result cap of 10, newest-first ordering, and the identity fields returned per match. It does not say what happens when more than 10 agents match (truncation vs. error, any paging), which is the one behavioral detail an agent would want.

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 tight sentences: what is searched, what comes back and in what order, then the alternative tool. Nothing is repeated and the result semantics are front-loaded after the core purpose.

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 output schema, the description correctly carries the burden of describing return values (chain, id, evidence layer, first/last seen dates) and the result count and ordering. The only omission is overflow/pagination behavior when the 10-match cap is exceeded, which would matter for a search 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 both parameters (query and chain) are already fully documented, including the enum values and the 2-64 character bounds. The description restates the query field categories but adds no syntax or format detail beyond the schema; the chain filter is not mentioned at all, though the schema covers it. 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?

States a specific verb and resource ('Search the agents Nooscape lists') and enumerates the searchable fields (name, endpoint host, registry key, wallet). It also names the sibling get_agent and the condition that selects it, so an agent can distinguish the two 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 final sentence routes the agent explicitly: 'Use get_agent for one agent's full record,' which is the only plausible alternative use case. The search scope (multi-match, up to 10) versus the single-record alternative is unambiguous.

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