KeyHalve - verify sealed documents

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

With annotations providing readOnlyHint=true, the description adds value by detailing exactly what the explanation covers (blind rail, three-share custody, commitments, revocation) and the optional topic focus. It does not contradict the read-only hint, and while it omits return format details, that is acceptable for a read-only explanatory 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?

The description is a single, information-dense sentence that front-loads the core purpose and includes substantive details (the trust rationale). Every clause adds value, with no filler or repetition.

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 simple tool with one optional parameter, full schema coverage, and no output schema, the description is complete. It explains the tool's purpose, the scope of the explanation, and the optional topic behavior, which is sufficient for correct use. Sibling context is not strictly necessary for an explanation 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?

The schema covers the single parameter (topic) with an enum and description, plus the parent description adds 'Optionally focused on one topic' - somewhat redundant. With 100% schema coverage, baseline 3 is appropriate; the description does not add new parameter semantics beyond what the schema already provides.

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 opens with 'Plain-language explanation of what a KeyHalve verification verdict means', which uses a specific verb (explain) and resource (verdict). It clearly distinguishes from sibling tools keyhalve_status and keyhalve_verify by focusing on understanding rather than checking or verifying.

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 provides clear context: it is meant for explaining a verification verdict and why it can be trusted. It does not explicitly state alternatives or when not to use it, but the purpose is unambiguous enough that an agent would know when to invoke it. A minor gap is the lack of explicit 'use verify for actual verification' note.

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 and openWorldHint, so the description's additional 'status only, no integrity or rail checks' provides useful context about what the tool does NOT do, going beyond the annotations. It also clarifies that it reports 'outside its validity window' as a status. Non contradicting and adds value, though it doesn't detail response format or error 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?

The description is two sentences, front-loaded with the core function, and every clause is informative. It includes the status outcomes, the sibling comparison, and usage guidance without redundancy.

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 partially covers return values by listing possible statuses (active, revoked, outside validity window) and even includes reason/time for revoked. For a simple status tool with one param, this is reasonably complete, though it doesn't specify exact response structure or error handling.

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% for the single parameter, and the schema already explains the document_id format with examples. The description just says 'by id' without adding further semantic detail, so it doesn't elevate beyond the baseline.

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 starts with 'Live status of a KeyHalve-sealed document by id' which specifies the verb (status check), resource (document), and scope (live status with three outcome categories). It explicitly contrasts with keyhalve_verify, noting this tool is 'lighter' and does not perform integrity or rail checks, clearly distinguishing it from siblings.

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 directly states when to use this tool: 'Use for "is this still good right now?"' and differentiates from keyhalve_verify by saying it's status-only vs. full verification. This gives explicit usage context and an implicit alternative, which is strong 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?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses critical behavioral traits: 'This tool NEVER decrypts sealed contents — any decryption key in the URL fragment is discarded unread; contents are only readable by opening the verify URL in a browser.' This adds significant privacy context and clarifies the tool's non-decrypting nature, which is beyond what annotations provide.

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 and front-loaded, starting with the core purpose. It uses three sentences to cover inputs, outputs, and a critical behavioral constraint, with no wasted words. Every sentence provides actionable 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?

Given a single-parameter tool with no output schema, the description is highly complete: it enumerates all accepted input types, lists the specific return fields (existence, live status, ciphertext integrity, attestation, validity window, issuer trust context), and explains the non-decryption behavior. This fully contextualizes the tool's operation and results.

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 input schema describes the parameter as 'A KeyHalve verify URL, QR-code text, or bare document id.' The description adds specific id prefixes (vp_…, kh_…, cb_…) and clarifies that it accepts the raw text of a QR code, enhancing the schema's coverage. With 100% schema coverage, this extra detail justifies a score above the baseline of 3.

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 function: 'Verify a KeyHalve-sealed document.' It specifies the exact verb (Verify) and resource (KeyHalve-sealed document), and lists accepted input forms. However, it does not explicitly distinguish itself from sibling tools like keyhalve_status or keyhalve_explain, so it lacks direct sibling differentiation.

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 context: it is for verifying sealed documents and returns a cryptographic verdict. It explains what inputs are accepted but does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or conditions. Thus, usage is implied rather than explicitly guided.

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