Concurrent-client isolation probe

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It hints that the verdict is 'latest' and 'signed' and 'on file,' but does not state whether the operation is read-only, what happens if no verdict exists, what 'signed' entails, or any permission or rate-limit considerations.

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 definition is a single front-loaded sentence with no filler, which is appropriately concise. However, the terseness leaves key usage and behavioral context unstated, so it is not maximally helpful.

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?

The tool has one parameter, no annotations, and no output schema. The description does not explain what a returned verdict contains, whether absence of a verdict is possible, or how the signed aspect affects usage, leaving meaningful gaps for an agent to infer.

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 endpoint parameter. The description only repeats that the verdict is 'for an endpoint' without clarifying the expected endpoint format, identifier syntax, or examples, so it fails to compensate for the missing schema documentation.

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 a retrieval of the latest signed verdict associated with an endpoint, giving a specific resource and scope. It does not differentiate this tool from the sibling tools verify_receipt or probe_isolation, so it falls short of a 5.

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 guidance on when to use get_verdict versus verify_receipt or probe_isolation, and no exclusions or prerequisites are mentioned. The endpoint parameter implies a lookup-by-endpoint use case, but that is the only hint.

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 burden. It does disclose that this is an active concurrent probe requiring operator authorisation and that the result is a signed verdict, which hints at intrusiveness and auth requirements. It says nothing about runtime, side effects on the target, whether the probe is disruptive, or failure modes.

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 two clauses: the action and the return value. Nothing is wasted, though terms like 'per-surface' are left undefined and add density without clarity.

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?

No output schema exists, and the description only gestures at the return value ('signed per-surface verdict') without explaining what a surface is or how the verdict is structured. For a potentially intrusive security probe with two undocumented required parameters, more context is needed to call it safely and 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 coverage is 0%, so the description must define both parameters. It loosely maps 'target' to the MCP server and 'authorisation' to operator approval, but never states whether authorisation is a token, signed grant, or scope string, nor what form the target takes (URL, name, endpoint).

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: runs a concurrent-client isolation probe against a target MCP server and returns a signed per-surface verdict. That is clearly distinct from get_verdict (retrieve) and verify_receipt (validate), though the description 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?

The phrase 'operator-authorised' implies a precondition: the target must already be sanctioned before probing, which is real usage signal. However, it gives no guidance on when to run a probe versus calling get_verdict or verify_receipt, and no exclusions or sequencing advice.

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 are provided, so the description carries the full disclosure burden and delivers almost nothing. 'Signed' faintly hints at cryptographic verification, but there is no statement on whether the call is read-only, permissions required, what happens on an invalid signature, or whether failure is an error versus a returned result — critical for a verification tool.

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 short front-loaded sentence with no filler, but the brevity is a symptom of under-specification rather than efficiency — there is nothing here for the agent to act on beyond the name.

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?

A tool taking a nested object, with no annotations and no output schema, and the description says nothing about the receipt shape or the return value (boolean, verdict, error). For a verification tool whose entire value is its outcome, the definition is effectively unusable as written.

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 0% and the single parameter is an untyped nested object with no documented properties. The description only echoes the parameter name ('receipt'), giving no structure, required fields, encoding, or format an agent would need to construct a valid receipt payload.

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 (Verify) and resource (signed verdict receipt), so the agent knows the general action. But it doesn't distinguish this from get_verdict, and 'verify' is ambiguous — cryptographic signature check, schema validation, or verdict replay are all plausible readings.

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, when-not-to-use, or alternatives named. The sibling get_verdict is presumably related (it produces the verdict that a receipt would attest to), but the description never explains the relationship or routes the agent between them.

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