dokimo-mcp

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered structurally. The description adds genuine value beyond annotations by disclosing what the card contains (skills, endpoints, A2A versions), which is useful behavioral context about what the returned document will describe. No contradiction with annotations.

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 sentence that leads with the verb 'Fetch', states the target, and appends a useful parenthetical definition of what an agent card is. Zero wasted words; every clause earns 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 zero-parameter, read-only discovery tool with comprehensive annotations and no output schema, the description fully equips an agent to call it correctly. Nothing about when, how, or what it returns is left ambiguous.

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 tool has zero parameters, so there is nothing for the description to clarify. Per the rubric, a 0-parameter tool gets a baseline of 4, and the description correctly stays silent on parameters rather than inventing unnecessary detail.

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 ('Fetch'), a specific resource ('Dokimo's public A2A agent card'), and explains what the card contains (skills, endpoints, supported A2A versions). The phrase 'discovery document' clearly distinguishes it from the verification-focused siblings (verify_evidence_package, recompute_merkle_root) without needing to open schemas.

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 this is the discovery step — you read the card to learn capabilities before verifying — but it never explicitly states when to call it versus the sibling verification tools. No exclusions or alternatives are named, so the agent must infer the usage context.

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, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds valuable context: it is purely local, performs no network or anchor check, and specifies the exact return shape {recomputed_root, merkle_scheme, steps}.

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 local-only constraint is front-loaded, then the algorithm, then the verification instruction. It is somewhat dense but every sentence carries functional information and nothing is wasted.

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?

Although there is no output schema, the description names the return fields, and it fully specifies the hashing scheme and verification procedure. An agent has everything needed to invoke and interpret the result.

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, but the description adds real meaning: it explains the leaf is hashed in the leaf domain (H(0x00 ‖ leaf)) and that proof_path is replayed with internal nodes hashed as H(0x01 ‖ left ‖ right), with side semantics restated. This algorithmic context goes beyond the schema's field-level definitions.

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+resource (recompute Merkle root) and immediately scopes it as local-only, explicitly contrasting with network and anchor-check behavior. The distinction from verify_evidence_package is clear from the 'no network call, no anchor check' framing.

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?

Tells the agent what to do with the result ('compare the returned root to the root in an evidence package yourself; if it differs, the package was tampered with'), giving clear usage context. It stops short of naming verify_evidence_package as the alternative for full package verification, leaving that inference to the agent.

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?

Goes well beyond the annotations by disclosing that the call leaves the process (public A2A endpoint), that the verdict is Dokimo's answer and is NOT signed, and that missing v2 fields silently downgrade the check to legacy v1. That last point is a non-obvious behavioral fallback an agent must know about before calling.

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?

Front-loads the core action, then follows with transport, required payload, and return shape in a logical order with no filler. It is a bit dense for one paragraph and the trailing line break is untidy, but every sentence carries 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?

No output schema exists, but the description compensates by sketching the return object (verified, checks: recompute, onchain_anchor, rule_version_bound) and the exact condition for verified=true. Combined with full parameter disclosure, an agent has everything needed to call and interpret it.

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 nested package schema already enumerates leaf, root, proof_path, rule_version_commitment, summary, binding and the optional close_id. The description largely restates those same keys, adding only slight emphasis on the v1/v2 implication, so baseline 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?

States a specific verb and resource: 'check one record of an evidence package against the on-chain anchor', and names what is being validated (Merkle proof + anchored commitment). The scope 'covers this one record only' plus the emphasis on on-chain anchoring clearly separates it from recompute_merkle_root and dokimo_agent_card.

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 clear context for use: submit a package to Dokimo's A2A endpoint to get a verdict, and states the scope limit ('this one record only'). It never explicitly names the sibling recompute_merkle_root as the lighter-weight alternative for a local recompute, so the routing is implied rather than spelled out.

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