Proof of Type Input

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

The readOnlyHint and openWorldHint=false annotations already establish a safe, closed-world read operation. The description adds useful scope about what content is covered, including proof guarantees and what it does not guarantee, privacy, and limits. It does not describe return format, depth, or how the answer is delivered, so a 3 is appropriate with annotations covering the safety profile.

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?

It is a single, front-loaded sentence listing the covered topics with no filler or repetition. The list is slightly run-on, but every item is meaningful and nothing extraneous is included.

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, read-only explanation tool with one optional enum parameter and no output schema, the description covers the conceptual scope adequately. It is still missing routing guidance versus get_quickstart and does not indicate what the agent receives back (e.g., structured text or sections). Given the presence of a closely related sibling, that omission matters.

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 the enum values already tell the agent the available topics with a default. The description loosely maps content to those topics (e.g., token claims for 'token', SDK options and events for 'sdk'), but it does not define what each enum value will return. Baseline 3 is correct.

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 enumerates the explanatory content covered: how Proof of Type Input works, proof guarantees and limitations, privacy, limits, token claims, and SDK options/events. That is much more specific than the generic tool name 'explain'. However, it does not distinguish this tool from sibling get_quickstart, so it stops 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 explicit guidance on when to use this tool versus get_quickstart or verify_proof. The topic enum provides some implicit context (overview, faq, token, sdk), but the description never states when this tool is the right choice or when another sibling should be used instead.

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 and openWorldHint=false, so the safety profile is covered. The description adds that the generated code verifies the proof server-side, which is useful context about the artifact returned, but it does not disclose anything further about the tool call itself.

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 tight sentences with the purpose front-loaded and the conceptual parenthetical placed where it aids comprehension. No padding, though the definition is short enough that it could afford one more sentence of routing guidance.

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 read-only code-generation tool with no output schema and a fully documented single parameter, the description covers what is produced ('ready-to-paste code') and what it proves. Only the absence of a pointer to the sibling verify_proof/explain tools keeps it from being fully complete.

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% with a single enum parameter that already documents its default; the description only echoes this with 'Pick a framework.' Baseline 3 applies since the schema does all the work and the description adds no syntax or selection guidance beyond it.

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 the resource clearly — 'ready-to-paste code to embed Proof of Type Input' — and the parenthetical defines the product concept so an agent understands what is being generated. It is not explicitly differentiated from the siblings (explain, verify_proof), but the resource itself is distinct enough to avoid confusion.

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?

'Pick a framework' gives minimal parameter-level guidance, but there is no statement of when to reach for this tool versus explain or verify_proof, nor any prerequisites or stated limits. Usage is only implied by the embedding/code-generation framing.

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 and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior: the token is an EdDSA JWT and the call returns who typed it, when, and the human score. It omits auth requirements, rate limits, and failure behavior, so it is good but not exhaustive.

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, front-loaded with what is verified, then what to pass, then what is returned. No filler and nothing redundant with the schema.

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?

There is no output schema, so the description carries the return-value burden and does so (who typed it, when, human score). It is nearly complete; the main missing piece is what the tool returns or raises when the proof is invalid or expired.

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. The description goes beyond the schema by explaining the semantic role of text and origin — verifying the proof is bound to exactly that text on that site — which clarifies why these arguments matter, not just their types.

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 precise verb and resource: 'Verify a Proof of Type proof token (EdDSA JWT).' It also names the exact purpose (confirm the proof is for that text on that site), so an agent immediately knows what the tool does and cannot confuse it with explain/get_quickstart.

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 gives clear invocation context: pass the text and site origin to bind the proof to exactly that text/site. It does not, however, state when not to use it or what to do on failure, and it implies text/origin are needed while the schema marks only token as required, which is slightly imprecise guidance.

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