GVE Public Governed Knowledge

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so much of the behavioral burden is lifted. The description adds that only the 'public' object is returned, which is useful scope information not in annotations, but doesn't discuss errors for missing ids, permissions, or rate 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?

A single, front-loaded sentence with no wasted words. Every clause earns its place by naming the resource and the linkage to search.

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 annotations and an output schema present, the description needs only to establish purpose and provenance, which it does. Missing explicit contrast with get_object is a minor gap given the low-complexity single-parameter shape.

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

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

Schema coverage is 100% and the single id parameter is fully documented in the schema with constraints. The description adds only the provenance hint ('returned by search'), which duplicates the schema description, 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?

States a specific verb (fetches) and resource (the full public object), and ties the input to the 'search' sibling by referencing an id returned by search. It doesn't explicitly distinguish itself from get_object, which is a close sibling and leaves ambiguity about when to use one over the other.

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 clearly implies the workflow: use after search to retrieve the full object for a returned id. It doesn't explicitly state when not to use it or contrast with get_object, but the search-provenance context is a clear usage cue.

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, non-destructive, non-open-world. The description adds genuine context beyond that: it notes the object is returned exactly as publicly served and discloses that freshness, confidence and relations come back as 'not established or not published', which tells the agent what to expect in the payload.

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?

One front-loaded sentence that leads with the primary return value and defers secondary detail to a parenthetical. It is dense but earns its words; no 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?

An output schema exists so return structure needn't be spelled out, and annotations cover the safety profile. The description adds the governance-view caveats, making it reasonably complete for a single-object read, though the absence of parameter and sibling-routing detail is a minor 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 only 33% – only 'id' is documented (as listed by list_objects), while 'type' and 'namespace' carry no schema description. The description adds nothing about any parameter's format, allowed values, or role, so 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+resource: returning one public governed object plus its governance view. It is clear what the tool produces, but it does not differentiate itself from the sibling 'fetch' or explain why one would use get_object over fetch, so an agent must infer the boundary.

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?

There is no explicit when-to-use guidance, no when-not-to-use conditions, and no alternatives named. The siblings fetch/search/list_objects are never referenced, so routing between them is left entirely to inference.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: the page size (100 per page) and the fact that supplying 'type' switches from a counts summary to a paginated object listing. It does not describe the return payload, but an output schema exists.

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, front-loaded with the core action, then the two modes in order. No filler or redundant restatement of the title.

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 full output schema and rich annotations, the description only needs to cover scope, modes, and pagination, and it does. It is essentially complete for calling the tool correctly, though it could note tenant scoping relative to list_tenants more explicitly.

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 is 3, but the description adds real semantic value: 'type' is not just a filter but a mode switch that changes the entire result shape, and 'page' operates in fixed 100-item pages. That is meaning beyond what the schema's per-field text conveys.

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 (lists) and resource (public objects of one tenant), and crisply distinguishes its two result modes based on whether 'type' is supplied. It does not name or contrast the sibling tools (get_object, search), so it falls just short of maximal sibling differentiation.

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 two-mode behavior ('without type' vs 'with type') implicitly guides the agent on which parameters to supply, which is useful conditional guidance. However, it never states when to prefer this tool over search or get_object, nor any exclusions, so usage is only implied.

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, non-destructive and closed-world, so the safety profile is covered structurally. The description adds that results are limited to public governed knowledge with per-tenant object types and counts, which is useful scoping context but nothing about pagination or freshness.

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?

One tightly-packed sentence with the resource front-loaded and the return shape appended; no filler. It is slightly dense with internal terminology, which costs a little clarity but not length.

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 an output schema present, the description needn't document returns in detail, and it does gesture at the payload. For a simple read-only listing tool the coverage is adequate, missing only a pointer to which sibling to call next.

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 no parameters, so there is nothing for the description to compensate for; the baseline for zero-parameter tools applies. The description correctly implies an unfiltered enumeration.

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 (Lists) and resource (organizations publishing public governed knowledge) plus what each entry exposes (object types and counts). It's clear what the tool returns, though the jargon 'GVE' is undefined and the differentiation from siblings like list_objects is not made explicit.

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?

No statement of when to use this tool versus the siblings fetch, get_object, list_objects, or search. The description never mentions alternatives or conditions, so an agent must infer that 'list all tenants' is a discovery/entry-point call.

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, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that: the match is lexical (not semantic) and is scoped to labels and descriptions only, and it states the return shape (identifiers for fetch). It omits pagination/matching behavior, but with annotations carrying the safety burden this is solid.

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

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

Two sentences, front-loaded with the core operation and the return contract, with zero redundant or filler text.

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-value detail is unnecessary, and the description still supplies the key hand-off fact (identifiers go to fetch). The remaining gap is the undocumented query/limit semantics, which matters for a search tool but is minor given the annotations and output 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 50%: only 'type' and 'namespace' are annotated, while 'query' and 'limit' carry only type constraints. The description adds no parameter meaning — it never explains query syntax (exact vs. prefix vs. multi-term), limit defaults, or how type/namespace constrain results — so it does not 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?

The description states a specific verb and resource — 'lexical search over the labels and descriptions of the public objects' — and notes it returns identifiers for fetch. It is clearly distinct from get_object/fetch (which retrieve by identifier) and list_objects (which enumerates), though it never names those siblings as alternatives.

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 'Returns identifiers to pass to fetch' implies the intended workflow (search then fetch), which is useful implied usage. However, it gives no explicit when-to-use versus list_objects or get_object, and no exclusions or prerequisites.

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