Verdict L402

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

With no annotations provided, the description carries the full burden and largely meets it: it declares the tool is advisory/read-only ('reads the command, it does not run it'), that it returns one of three dispositions, and that intent can be supplied. It does not cover auth requirements, latency, or failure behavior.

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: the trigger, the enumerated risk categories, the intent hint, and the scope caveat. Front-loaded and free of padding, though the opening 'Free sample.' is promotional rather than informative and does not earn 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?

For a two-parameter classification gate with no output schema, the description covers trigger, scope, non-execution, and the possible dispositions, which is enough for an agent to call it correctly. Minor gaps remain on response shape details and any limits on command length or rate.

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, and the description adds genuine value by advising when to supply 'intent' ('Pass the human intent when you know it'), implying it improves the judgment rather than being required. It does not add format or syntax detail 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 concrete verb and resource: it asks whether to 'allow, review or block' a shell command before an agent runs it, and enumerates the risk categories it judges (root deletion, download and run, privilege escalation, secret exfiltration). The 'Not a sandbox' clause sharpens the boundary, but it does not distinguish this gate from the sibling verdict_firewall/verdict_guard/mcp_vet tools.

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 a clear trigger ('Before a coding agent runs a shell command') and concrete motivating cases for invoking it. It also rules out a likely mis-assumption ('Not a sandbox: it reads the command, it does not run it'). It stops short of naming when to prefer a sibling tool or any exclusions beyond that.

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 burden. It usefully discloses the outcome space (allow, review, block) and the detection behavior (catching hidden orders in content), which the agent would otherwise have to guess. It omits auth requirements, latency, and what consumer action a 'block' or 'review' obligates, keeping it just short of a 5.

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 trigger and followed by the return contract — the structure is efficient. The leading 'Free sample.' is unexplained marketing noise that does not earn 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?

With no output schema, the description fills the gap by enumerating the three verdict results, and the input parameters are fully documented in the schema. For a low-complexity, three-required-parameter tool the coverage is adequate; only the handling of review/block outcomes is left unstated.

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 100%, so the schema already defines goal, action and content. The description restates these in prose ('give the human goal, the content it read and the action it proposes') but adds no format, length, or sizing guidance beyond the schema. Baseline 3 applies when structured fields do the heavy lifting.

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 function: given goal, content and proposed action, it returns allow/review/block to catch actions driven by injected instructions. That is a concrete verb+resource an agent can act on. It does not differentiate itself from siblings verdict_command_gate, verdict_guard, or verdict_mcp_vet, 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?

It gives an explicit trigger condition — 'Before an agent acts on untrusted content (pay, send, delete, click, reply)' — which is a clear context for use. It names no alternatives among the sibling verdict tools and states no when-not-use case, so it is strong but not complete.

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 must carry the behavioral burden, and it does disclose the output contract (allow/review/block with scores and reasons) and a constraint (free sample). It omits operational details such as rate limits beyond the sample tier, whether submitted text is logged or retained, and latency, but for a stateless analysis tool the essentials are present.

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?

Four short sentences, each doing distinct work: scope, threat classes, return values, and routing. The 'Free sample.' opener is slightly cryptic as a lead and the tier limitation is only fully clear once the schema is read, but nothing is redundant.

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, yet the description explains the return shape (three verdict levels with scores and reasons), which is what an agent most needs. Combined with the routing guidance and single well-documented parameter, only minor operational details are absent.

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 100% schema description coverage, so the schema already defines 'text' and its 4000-character free-sample cap. The description adds only a selection heuristic ('text you did not write'), which is useful framing but not syntax or format detail beyond the schema. 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 (check) plus the exact resource (untrusted text such as web pages, emails, documents, tool output) and enumerates the threat classes it detects. It also names the sibling it is not (verdict_firewall), so an agent can route without opening any schema.

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?

Explicit trigger ('before your agent reads untrusted text'), explicit scope ('use it on text you did not write'), and an explicit exclusion with the correct alternative ('Do not use it to judge an action: use verdict_firewall'). This is a full when/when-not/alternative statement.

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. It does disclose the response shape (allow/review/block with reasons) and hints at a pricing/tier model via 'Free sample,' which is useful context. It does not say whether the tool only analyzes supplied text or actually reaches the network, whether inputs are retained, or any rate limits on the free tier.

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, no padding, and the output contract is stated compactly at the end. 'Free sample.' is a slightly odd lead that delays the actual purpose, but it is brief enough not to harm usability.

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 4-parameter analysis tool with no output schema and no annotations, the description covers the key facts: what it inspects, when to run it, and what verdicts it can return. It could be stronger on data handling and on routing versus the sibling tools, but nothing essential to calling it is missing.

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 every parameter (name, tools, description, permissions) is documented in the schema itself, so the baseline is 3. The description adds no syntax or format detail beyond what the schema already provides; notably it never mentions the optional tools[] or permissions[] inputs.

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 (vet) and resource (an MCP server/skill/tool description) and enumerates what it inspects: poisoned descriptions, hidden orders, excessive permissions, look-alike names. It also names its output form (allow/review/block). It does not, however, distinguish itself from the similarly named siblings verdict_guard, verdict_firewall or verdict_command_gate, so the agent must guess which of the four handles this case.

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 an explicit trigger point: 'Before installing an MCP server, skill or tool.' That is genuine when-to-use guidance. It stops short of saying when not to use it or which sibling to prefer for adjacent cases (e.g. runtime gating vs. pre-install vetting).

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