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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Describe' weakly implies a read-only lookup, but the description never states that, nor does it cover permissions, behavior on an unknown/expired handle, or what the returned capability metadata represents.

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 filler or redundancy. It is tight, though its terseness comes at the cost of the guidance captured under other dimensions.

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 tool takes only one required string. However, with no annotations and no statement of how to obtain a handle or what happens on an invalid one, the definition is thin for an agent trying to use it correctly in sequence after list_capabilities.

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?

One parameter with 0% schema description coverage; the description only restates that the handle identifies a specific capability. It adds no meaning about the 44-character base64 format or where valid handles originate, so the agent gains nothing beyond the schema's own type constraints.

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 ('Describe') and resource ('credential-use capability'), plus the lookup key ('by handle'). The word 'one exact' implies a single-item fetch versus the sibling list_capabilities and invoke_capability, though those siblings are never named.

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 or when-not-to-use guidance, and no mention of the sibling alternatives for listing or invoking capabilities. The phrase 'by handle' hints that a handle is a prerequisite, but where that handle comes from (presumably list_capabilities) 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?

No annotations, so the description carries the burden and largely does: it discloses the origin/prefix scoping granted by the handle, the per-mode argument shapes, the SSH byte range (1-4096), and a replay/ejection warning. It does not cover error behavior or what a response contains, which is acceptable given 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?

Front-loads the core action in the first sentence, then dispatches mode by mode with no filler. Dense and long, but this is a 7-parameter polymorphic tool and every clause conveys a rule the agent needs; the SSH byte range is the only slightly noisy detail.

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 7-param, 0%-coverage, nested-object schema with an output schema present, the description covers mode selection, optionality, scoping and a safety rule. It omits how handles are obtained and any error/failure semantics, which are the remaining gaps.

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 compensate, and it does: it maps handle, method, path, query, headers, body_base64 and payload onto their respective modes and marks which are optional. It does not spell out the payload/method mutual exclusion that the schema encodes, leaving one inferential step.

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 ('invoke') and resource ('the exact capability named by handle'), and goes further by breaking the resource into dispatch modes (http_request, http_broker, attestation, SSH). It never names the siblings, but the action/read distinction against describe_capability and list_capabilities is obvious from the verb alone.

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 per-mode guidance: http_request takes only handle, http_broker takes method/path plus optional query, headers, body_base64, attestation takes a base64 payload, SSH takes one unframed base64 SSH-agent message. Adds an explicit 'never replay an ambiguous or cancelled invocation' rule. It stops short of saying when to prefer this over the describe/list siblings.

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 no annotations, the description carries the full behavioral burden, yet only 'List' implies a read-only, non-mutating operation. It adds the useful scoping detail that results are 'this endpoint's' credential-use capabilities, but says nothing about scope breadth, permissions, or whether the list can be filtered.

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 focused sentence with no padding, front-loaded with the verb. Its brevity is appropriate, though that brevity is also what leaves the meaning of 'capabilities' unstated.

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 lack of parameters keeps the contract simple. What is missing is any routing help against describe_capability and invoke_capability, which is the main decision an agent must make among these three siblings.

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 to document and the description cannot compensate for a gap that does not exist. Baseline 4 applies for a zero-parameter tool.

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 pairs a specific verb ('List') with a specific resource ('this endpoint's credential-use capabilities'), which is enough for an agent to grasp the operation. It does not, however, explicitly distinguish itself from describe_capability or invoke_capability, and 'capabilities' is left largely undefined, so sibling differentiation is only implied.

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 when-to-use guidance, no prerequisite, and no mention of the sibling tools. An agent must infer that this is the enumeration step used before describe_capability or invoke_capability.

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