Network Evidence MCP

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

Annotations already carry readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so safety/idempotency is covered. The description adds substantive context beyond that: outcome depends ONLY on supplied snapshots, the server observes nothing, no ranking/recommendation, and invalid/incoherent input 'fails closed with a coded error'. It omits auth/rate-limit details, so not a full 5.

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 and keeps to a single dense paragraph where each clause carries real information (scope, determinism, failure mode). It is verbose and run-on in places, but nothing is filler or tautological.

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 highly complex tool with nested objects, an output schema, and full annotation coverage, the description supplies purpose, determinism, boundary conditions, and failure semantics; the output schema covers return values. The one gap is explicit when-to-use/routing guidance against sibling tools.

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%, so the schema already documents the 5 parameters (bounds, wire format, canonical-identity requirement, requirements semantics). The description restates the candidate composition (network + ResolverManifest + CapabilitySnapshot) and the 1..16 bound but adds little syntax or format detail beyond the schema — baseline 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?

States a specific verb+resource ('Runs the real @nec/discovery discoverNetworks ... over 1..16 EXPLICIT ... candidate contexts') and names the precise output ('Core-built, Core-verified DiscoverNetworksResult with digests and per-candidate eligible/conditional/ineligible'). It also delineates what the tool is not ('observes nothing', 'does NOT choose, rank or recommend'), which separates it from ranking/selection tools.

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?

Conveys implied preconditions (candidates must be EXPLICIT, complete, already-derived; preflight is external) but never states explicitly when to call this versus its siblings (get_reviewed_evidence_case, list_network_profiles). The exclusions are negative rather than routing guidance, leaving the agent to infer the triggering 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 readOnly, idempotent, closed-world and non-destructive behavior, so the bar is lower, yet the description still adds real context: the data is checksum-pinned and shipped, returned verbatim with limitations/unavailable/unknown states and nonClaims preserved, plus source provenance and an explicit label. The historical-vs-synthetic distinction and the 'not live evidence' warning are behavioral facts an agent cannot get from annotations or schema.

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-loaded with the core action ('Returns ONE case by exact id'), followed by source, payload guarantees, and the historical/synthetic caveat in short declarative sentences. The middle clause is dense with parenthetical detail, but each sentence carries distinct information with 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?

Output schema exists, so return-value structure needn't be restated, yet the description still characterizes the payload (envelope verbatim, provenance, label). Combined with the pinned source path, id semantics, and the 'not live evidence' caveat, nothing an agent needs to call and interpret this single-param read tool 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% and the enum already constrains values, so the baseline would be 3. The description goes further by explaining why exactness matters (no fuzzy matching) and by giving the semantic meaning of each id — past public-network observations versus a synthetic fixture — which the enum alone does not convey.

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 ('Returns ONE case by exact id') and enumerates the exact valid ids, including what each one is (historical export vs synthetic fixture). An agent can distinguish this read-one-case tool from discover_network_candidates and list_network_profiles 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?

Gives clear invocation constraints ('exact id; no paths, no prefixes, no fuzzy matching') and a critical usage caveat that 'No case is live evidence', which shapes when the result is appropriate to rely on. It does not, however, explicitly name an alternative tool or say when to prefer those siblings over this one.

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 readOnly/idempotent/closed-world annotations by disclosing the critical epistemic constraint: no observation occurs, every currentSupport/currentAvailability is 'not_assessed', and membership must not be read as live availability. That single caveat prevents the most likely misuse of the 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?

Front-loads the resource and its fixed/canonical nature, then two short sentences carrying the two most important caveats. The inline chain-ID enumeration makes the first sentence dense, but every clause conveys scope an agent needs.

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 structure need not be restated, and the description covers the interpretive facts the schema can't: the profile set is fixed, the data is declared rather than observed, and availability is not asserted. Nothing needed to call 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?

Zero parameters, for which the baseline is 4. The description correctly and explicitly confirms "Takes no arguments," matching the empty schema with additionalProperties:false.

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?

Specific verb+resource ("Returns the FIXED public profile inventory") with the exact enumerated scope of chains and what each entry carries (resolver manifest DECLARED capabilities and truth boundaries). The capitalized "FIXED" implicitly separates it from discover_network_candidates, the dynamic-discovery sibling.

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 framing ("FIXED", "Nothing is observed", "Profile membership is not live availability") strongly implies this is the static-inventory tool to use instead of live probing, but no sibling is named and no explicit when-to-use/when-not condition is stated. Usage is inferable but not spelled out.

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