mcp-agentcore

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

With no annotations provided, the description carries the full burden. It discloses returned values (principal identity, delegation depth, cert validity, tool authorization) and implies a read-only verification through the verb 'Verify', but it does not explicitly state side effects, permissions, or error cases. This is adequate but not rich.

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-loads the main purpose, and each sentence adds value. No fluff or redundancy; it earns a top score for conciseness.

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 correctly lists the return fields. It also explains the purpose and regulatory context, making it fairly complete for a simple read-only tool. It misses minor aspects like error conditions or prerequisites, but these are not critical for a verification 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 both parameters with descriptive text (agent_pk as Ed25519 key, tool_name as intended tool), achieving 100% coverage. The description adds little beyond the schema, so the baseline of 3 is appropriate.

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 uses a specific verb 'Verify' with a clear resource ('human → agent delegation chain') and adds the specific check of whether a tool is whitelisted. This distinguishes it from sibling tools like generate_audit_proof and verify_jurisdiction by focusing on the delegation chain and authorization question.

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 clearly anchors usage to the regulatory question 'Did a real human authorize this AI action?', providing a strong context for when to use the tool. However, it does not explicitly mention alternatives or when not to use it, so it falls short of a 5.

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 discloses important behavioral aspects: the return contents (cryptographic audit chain, Merkle epoch roots, delegation certificate, trust score, violation history) and a validation field (chain_verification.is_valid) that proves tamper-resistance. It does not mention side effects or permissions, but 'generate' implies a read/compute operation, making the disclosure reasonably adequate.

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 three sentences, tightly packed with essential information: what it does, what it returns, and a key validation field. No redundant or filler content. Front-loaded with the action and regulatory context.

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 there is no output schema, the description lists the main return items and even highlights a verification field, which helps the agent understand what to expect. It lacks detailed instructions on how to use the returned bundle, but for a generation tool this is fairly complete. The regulatory context and tamper-proof guarantee add completeness.

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 already documents all three parameters with descriptions (100% coverage), so parameters are well-defined. The description does not add parameter-specific meaning beyond the schema, which is acceptable given the schema quality. It only broadly references 'reporting period' implicitly via Art. 12 record-keeping.

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 identifies the tool as generating a compliance evidence bundle for specific EU AI Act articles (Art. 12 and 14). It uses a specific verb ('generate'), names the resource (compliance evidence bundle), and distinguishes it from sibling tools that check or verify rather than generate.

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 for regulatory submission and compliance evidence. It implies when to use it (when an audit proof bundle is needed) but does not explicitly compare with check_delegation_chain or verify_jurisdiction. No exclusions or alternatives are mentioned, but the purpose is distinct enough to infer usage.

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 provided, the description carries the full transparency burden. It explicitly lists the validation criteria (signature validity, temporal bounds, H3 cell authorization, facet authorization) and states the return type, giving a solid picture of behavior. It does not mention side-effects or failure modes, but as a verification tool it is implicitly read-only and the description is transparent about its checks.

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: the first front-loads the purpose and the second details the checks and output. Every sentence earns its place with no fluff 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?

The description adequately covers the tool's purpose, key inputs, and high-level output. Given the absence of an output schema, saying it returns a structured result indicating whether the agent may proceed is sufficient for an agent to invoke it correctly. It does not cover error cases, but the complexity is moderate and the description is complete enough for selection and invocation.

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 already provides descriptions for all three parameters, covering 100% of them. The tool description reinforces the roles of h3_cell as territory and facet as authorization but does not add meaning beyond the schema, so a baseline score of 3 is appropriate.

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 uses a specific verb 'Verify' and clearly identifies the resource (H3 territorial cell) and the subject (AI agent authorization). It distinguishes itself from sibling tools by naming the specific certificate checks performed, making it clear that this tool is for authorization verification rather than chain checking or proof generation.

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 clearly implies when to use the tool: when verifying an agent's authorization in a specific H3 cell. It provides clear context but does not explicitly exclude alternatives like check_delegation_chain or generate_audit_proof, so it misses full when-not guidance.

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