Bench Agent Discovery

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

Annotations declare read-only, idempotent, non-destructive; description adds value by detailing exactly what data is returned, going beyond 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?

Single, well-structured sentence with zero wasted words; front-loaded with the core action and detailed data points.

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?

Despite no output schema, the description fully lists what is returned; annotations cover safety; parameter is fully described; no gaps for a simple 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 covers 100% of the single required parameter with a clear description of handle format; the main description does not add extra parameter guidance.

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 explicitly lists all returned data (recipe, manifest, invocation status, telemetry, benchmarks), distinguishing it from siblings like list_benchmarks and search_agents.

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?

Clear when to use (retrieve detailed info for a specific agent) but no explicit when-not-to or mention of alternatives beyond sibling context.

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 some behavioral context (public, versioned, trusted-runner-verified) beyond the annotations, but the annotations already clearly indicate read-only, idempotent, and non-destructive behavior. There is 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 a single 14-word sentence that immediately conveys the tool's purpose. It is front-loaded with the key action and resource, and contains no extraneous 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?

With no parameters and no output schema, the description covers the essential purpose. Annotations handle safety. However, it doesn't mention pagination, ordering, or whether the list is exhaustive, which might be needed for full completeness.

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?

There are no parameters (0), and schema description coverage is 100% (empty). The description does not need to explain parameters; baseline for 0 parameters is 4. It adds clarity on what is listed but not on filtering or sorting.

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 specifies the verb 'List' and the resource 'public, versioned benchmark contracts' with a clear scope 'only their trusted-runner-verified submissions'. It fully distinguishes from sibling tools 'get_agent' and 'search_agents' which deal with agents, not benchmarks.

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 for listing benchmarks but does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention when not to use it. No exclusions or alternatives are given.

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, etc. The description adds one behavioral detail: 'Owner telemetry and controlled benchmark evidence are returned separately.' This provides useful context beyond annotations, but does not fully disclose all behaviors (e.g., pagination, default sorting).

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 concise: two sentences, no wordiness. It front-loads the purpose and then adds a behavioral note. Every sentence contributes value.

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 12 parameters and no output schema, the description lacks details on return format, pagination, sorting behavior, and how parameters interact. It is adequate but incomplete for a complex 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 58% (7 of 12 parameters have descriptions). The description lists searchable dimensions (task, capability, etc.) which align with some parameters, adding context. However, it does not explain parameters without schema descriptions (e.g., sort, limit, maxP50LatencyMs) beyond what the schema provides, so it partially compensates but not fully.

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 the tool's purpose: to find public agents by multiple criteria (task, capability, category, etc.), distinguishing it from sibling tools like get_agent and list_benchmarks. The verb 'Find' and resource 'public agents' are specific and unambiguous.

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 does not provide any guidance on when to use this tool versus alternatives (e.g., when to use get_agent for a specific agent or list_benchmarks for benchmarks). No when-not-to-use or contextual exclusions are mentioned.

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