Bureau public reader

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds one genuine piece of behavioral context — that this read does not constitute a database health claim — which usefully bounds expectations, but it omits any detail about what the capability/admission read returns or how fresh it is.

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 the verb and subject first and the qualifier trailing; no filler. The trailing clause is slightly cryptic but it carries real information rather than padding.

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 described, and the zero-parameter schema is trivially complete. However, for a discovery entry-point tool with four siblings, the description should say more about when it is the right first call and what 'capabilities/admission' concretely covers; that gap keeps it at minimum-viable.

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, so per the rubric the baseline is 4; there is nothing for the description to disambiguate. Schema coverage is 100% with no properties, so no compensating text is required.

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 (Read) and resource (Bureau capabilities and configured admission), which is clearly distinct from the sibling tools that fetch artifacts, cases, or agents. The phrase 'configured admission' is somewhat opaque jargon, and it does not explicitly contrast itself against the sibling tools, but the intent is recoverable.

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 statement of when to call this versus the four sibling tools, nor any prerequisite or ordering guidance (e.g., 'call this first before using other Bureau tools'). The only boundary given is the negative constraint about database health, which is a scope limit rather than usage 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds one genuinely useful behavioral note — 'References are not fetched' — warning that reference expansion should not be expected, but supplies nothing else about access or constraints.

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

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

Two short sentences with no filler, and the core action is front-loaded. The structure is efficient, though the extreme brevity leaves gaps that fuller phrasing could have covered.

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. But with 0% parameter coverage, no usage guidance, and a name/description terminology mismatch ('artifact' vs 'Context Packet'), the definition is only minimally complete for an agent to select and invoke it confidently.

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

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

Schema description coverage is 0% for the single parameter; only the UUID pattern is self-documenting. The description never explains what artifact_id represents or where the caller obtains it (e.g., from bureau_discover or search results), so it adds no meaning 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?

States a specific verb (Read) and resource (one Context Packet), so an agent knows this retrieves a single item. However, the description calls the resource a 'Context Packet' while the tool name says 'artifact', and it never contrasts itself with sibling bureau_get_case, so differentiation is incomplete.

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 when-to-use guidance, no prerequisites, and no named alternative. The reader must infer that this is a single-item fetch versus bureau_get_case or bureau_discover entirely on their own.

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 'no claim or state change' largely restates them. The one genuinely new signal is 'visible contributions', implying access-controlled filtering of what is returned, but nothing is said about error behavior for missing or private cases.

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 with no filler; every clause carries information and nothing is repeated.

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 and annotations are rich, so return values and safety need not be spelled out. What remains thin is the meaning of case_id and the behavior when a case is not public or not found.

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% for the single required case_id, so the description must carry that burden. It never explains the identifier beyond implying it names a case, leaving the UUID format to be inferred from the schema pattern.

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?

Specific verb 'Read' plus a clearly scoped resource: 'one public Case and visible contributions'. The singular 'one' implicitly separates it from the sibling list tool bureau_list_cases, though no sibling is named outright.

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 versus bureau_list_cases, bureau_get_artifact, or bureau_search_agents. The only hint is 'no claim or state change', which rules out mutation but gives no positive usage condition or prerequisites.

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 the read-only, idempotent, non-destructive profile, so the bar is lower; the description still adds real behavior beyond them: the quarantine exclusion, the fact that claimability is computed against server time, an explicit reassurance that stored state/version and write authorization are unchanged, and a warning that pagination is an unstable view. That last point is exactly the kind of caveat an agent needs and cannot get from 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 short sentences, purpose first, then the status caveat, then the pagination caveat; no filler and nothing buried. The middle sentence compresses two distinct ideas (server-time evaluation plus a non-mutation guarantee) into one clause, which is slightly dense but still 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?

An output schema exists, so return shape need not be described, and annotations cover the safety profile. What remains missing for a four-parameter list tool at 0% schema coverage is any indication of 'capability' semantics and what happens with limit/after defaults, and there is no signal for choosing this tool over search_agents.

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

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

Schema description coverage is 0% across four parameters, so the description is the only source of meaning; it partially compensates by explaining the non-obvious 'claimable' enum value and the cursor/'changing view' behavior behind pagination. It says nothing about 'capability' or about 'limit' beyond the schema's own 1-50 bounds, leaving two parameters semantically opaque.

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

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

States a specific verb and resource ('List ... Cases') and qualifies the scope with two filters (public, non-quarantined), so an agent knows exactly what set is returned. It does not name or contrast itself with the singular retrieval sibling bureau_get_case, so the reader must infer the split rather than being told 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 gives genuinely useful selection semantics for one status value ('status=claimable selects open or expired claimed Cases using server time'), which tells an agent when that filter is the right one. However it offers no when-to-use/when-not guidance against the siblings (bureau_discover, bureau_get_case, bureau_search_agents), so overall routing is left 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description still adds genuine context beyond them: the consent/quarantine filtering and the important data-trust caveat that "Capabilities are self-reported." It stops short of describing pagination or result shape.

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

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

Two short, dense sentences with zero filler, front-loading the search scope ahead of the data-quality caveat. Every clause earns its place.

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

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

An output schema exists, so return values need no explanation. However, with three fully undocumented parameters at 0% coverage and no pagination or filtering guidance, the definition is only minimally complete 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 0%, so the description must carry the burden for the three parameters (after, limit, capability), yet it explains none of them. The phrase "Capabilities are self-reported" only obliquely hints at the capability filter and leaves cursor/pagination semantics undocumented.

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 gives a specific verb ("Search") and resource ("consented, non-quarantined public profiles"), clearly stating scope. It does not, however, distinguish this tool from the sibling bureau_discover, leaving the agent to 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 mention of alternatives such as bureau_discover, and no prerequisites. Only a scope constraint (consented, non-quarantined) is given, which implies a directory search but offers no routing logic.

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