Mifori CertAgent

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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, and the description adds substantial context beyond them: <50ms latency, no authentication/payment/rate limits, inclusion of private certificates (public=false), and Ed25519 asymmetric verification against a named JWKS endpoint.

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 dense sentences that front-load the core lookup behavior and then the mode-selection rule. Every clause carries information, though the first sentence packs several independent facts (latency, cost, private certs) into one run-on.

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 an output schema present and annotations covering the safety profile, the description need not explain return shapes. It fully covers both invocation paths, verification mechanism, and access conditions, leaving nothing an agent needs in order to call it correctly.

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 interaction semantics the schema lacks: eval_id used alone is mutually exclusive with agent_id+limit, and it clarifies agent_id accepts a DID or target_bot_url. It adds mode-selection meaning beyond the per-parameter schema text.

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?

Names a specific verb (retrieves/validates/lists) and resource (signed audit certificate, public audit history), and clearly delineates the two operations. It is easily distinguished from siblings like get_agent_leaderboard or verify_agent_reputation.

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?

Explicitly states the two invocation modes: pass eval_id alone for a single-certificate lookup, or pass agent_id with limit for history. This gives clear context for selection, though it does not name or exclude the sibling tools by comparison.

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 cover readOnly/idempotent/non-destructive, but the description adds meaningful behavior: no auth required, endpoint-level deduplication, exact sort order, and the shape of each entry (protocol_detected, verified_capabilities). It stops short of discussing rate limits or result freshness, which would be the final missing piece.

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 dense sentences that are front-loaded with the core action and ordering, then filtering behavior. Every clause carries information, though the protocol name examples ('MCP 2.0', 'Mifori Cognitive v1') are slightly expendable.

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?

An output schema exists, so return values needn't be described, and the description instead covers the auth model, sort order, and filter semantics. It is essentially complete for a read-only search tool; only result freshness/pagination caveats 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?

Schema coverage is already 100%, so baseline is 3. The description adds real value by enumerating example query values ('wiki', 'search', 'cloudflare', 'crypto', 'docs') and clarifying that query matches tool capability, DID, or domain, plus reiterating the tier filter semantics.

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 (queries) and resource (verified MCP servers / autonomous AI agents) and even specifies the ordering semantics (Synthetic IQ descending, latency ascending) and deduplication rule. This clearly distinguishes it from siblings like get_agent_certificate and verify_agent_reputation.

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?

Explains the context of use well: it is a free, unauthenticated snapshot, and it tells the agent to pass a query to filter by capability/DID/domain and optionally a tier. It does not explicitly say when to prefer this over the sibling tools, but the surrounding context is clear enough to route correctly.

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=false, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-schema context: sub-100ms persistence, no authentication or payment required, and that a single-use reward token is returned for verify_agent_reputation. It does not, however, address the idempotency hint's implications (e.g. whether repeat calls re-issue tokens).

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 front-loaded sentences that lead with the action, the performance/auth characteristics, and the reward, then cover the sandbox usage pattern. Dense but every clause carries operational information; no filler.

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 an output schema present, return values needn't be explained, and the description supplies the auth, latency, and token-grant behavior an agent needs before calling. The only mild gap is the unaddressed idempotentHint interaction with the single-use token claim.

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 intent behind eval_id='sandbox'/'onboarding' and tying reported_issue to the described use case, which helps the agent pick the right argument values rather than 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 specific verb and set of resources: persisting telemetry, score disputes, and sandbox credit requests, plus the concrete side effect (granting a 'mfr_fbk_...' token). It references verify_agent_reputation as the consumer of the token but never explicitly contrasts itself with the read-only siblings, so it stops short of full 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?

Gives a clear condition for the sandbox path: 'First-time evaluators without a prior audit or dispute can pass eval_id=sandbox', and frames the alternative as fabricating a complaint. It covers the two main modes (telemetry reporting vs. initial credit request), though it doesn't state when *not* to call it or how it relates to get_agent_certificate/get_agent_leaderboard.

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 declare non-read-only, open-world, non-idempotent, non-destructive; the description adds the behavior that matters: this is a paid, meterable operation with a two-step quote/pay flow, returns an Ed25519-signed certificate, publishes to a public leaderboard unless public=false, rejects non-agent REST URLs with 0 points, and holds bearer tokens strictly in-memory. This is far richer than the annotations alone and consistent with them.

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 main action is front-loaded and every clause carries load-bearing information (protocols, payment, privacy, rejection rule). It is, however, a single dense paragraph with heavy nested parentheticals and semicolon chaining, which makes it harder to scan than a segmented version would be.

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?

An output schema exists, yet the description still summarizes the return artifact (Ed25519-signed eval_id certificate) and covers payment, auth via target_bearer_token, privacy, and protocol scope. For a six-parameter, payment-gated operation, nothing an agent needs to invoke it correctly 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%, so the baseline is 3, but the description adds real meaning: it explains the two-step workflow in which omitting payment_proof yields a 402 quote and setting it to an 'mfr_fbk_...' token or Base USDC hash accepts payment, and it clarifies the consequence of public=false. That is genuine semantic value beyond the schema text.

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 ('Executes a live multi-protocol audit against target_bot_url') and enumerates exactly what is benchmarked (Synthetic IQ, latency, schema compliance, tool capabilities) and what is returned (signed certificate with eval_id). It also names the sibling submit_agent_feedback as the route to a free credit token, so an agent can differentiate it from get_agent_certificate/get_agent_leaderboard 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?

Provides explicit when-to-use routing: (1) call with target_bot_url alone for a free PAYMENT_REQUIRED_402 quote, or call submit_agent_feedback with eval_id='sandbox' for a free token; (2) call again with payment_proof. It also states the condition that selects the confidentiality path (public=false) and that static REST URLs are rejected, leaving nothing to inference.

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