first-epss-mcp-server

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

Goes well beyond the readOnly/idempotent annotations: discloses the 500-unique-entry processing cap, that response byte limits can return fewer whole entries, the exact resume protocol, and the semantics of deferredCves, withheldCves, previews, and unknown scores. These are non-obvious batch behaviors an agent cannot infer from structured fields.

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 leads with the core purpose and then packs pagination, response-partitioning, and alternative-tool guidance into short clauses without filler. It is dense – several concepts per sentence – but every sentence carries operational information for a batch tool.

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 explains the response partitioning (deferred/withheld/missing) and how to continue iterating, which is exactly the extra context an agent needs for a paginated batch call. Nothing required to invoke or resume it correctly is left unexplained.

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: batchOffset is a resume cursor into first-occurrence normalized unique order, capped at 500 processed entries, and must be paired with the original cves and returned score date. That constrains usage in a way the schema's plain integer description does not.

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 (retrieve) and resource (FIRST EPSS probability and percentile) for supplied CVEs, and immediately scopes it to either latest or historically dated data. This distinguishes it from epss_get_timeseries (temporal series) and from epss_list_reference, which it names as the coverage/interpretation tool.

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 concrete operational guidance: resume with nextBatchOffset as batchOffset, resubmit original cves and returned score date, and use epss_list_reference for coverage and interpretation. It does not explicitly say when to prefer epss_get_timeseries or epss_prioritize_cves instead, so the sibling routing is partial rather than complete.

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/openWorld, and the description goes well beyond that: byte limits that retain whole history items, the distinction between withheldCves (processed) and deferredCves (not queried), previews, and the caveat that re-anchoring snapshots may be unavailable. The one weakness is that it says 'up to 50 unique CVEs' while the schema accepts maxItems 5000, which leaves batch size ambiguous.

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?

Purpose is front-loaded in the first sentence, but the rest is a dense run-on chain of jargon-heavy clauses ('Response byte limits retain whole history items', 'Model boundaries do not explain score movement') that packs many distinct facts without structure. Nothing is wasteful per se, but readability suffers and key limits are buried.

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 paged, read-only, open-world tool with an output schema, the description supplies the resume protocol, partial-result semantics, and the re-anchor fallback, which is close to complete. The unresolved '50 unique CVEs' versus schema maxItems 5000 mismatch is the main gap an agent would want clarified.

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 baseline is 3, but the description adds real semantics: batchOffset is a first-occurrence normalized-order resume key that must be paired with the original cves and returned score date, and date refers to the returned score date when resuming. It also describes response fields (nextBatchOffset, withheldCves, deferredCves) that are not in the input schema, which is useful context.

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 first sentence states a specific verb and resource: retrieve an EPSS anchor plus up to 30 preceding daily observations for CVEs, batched via batchOffset. That clearly distinguishes it as a time-series tool. It never names any sibling (epss_get_scores, epss_query_threshold) as an alternative, so differentiation from siblings is left to inference.

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?

Usage is implied by the resume instructions ('Resume CVE batches with nextBatchOffset as batchOffset...') and by re-anchoring guidance, but there is no explicit statement of when to choose this over epss_get_scores or epss_query_threshold. An agent must infer that this is for history/deltas while siblings return point scores.

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 safety is covered. The description adds genuinely new context beyond that: the content is static reference material rather than live EPSS data, and it enumerates the four subject areas returned, which tells the agent to expect documentation, not scores.

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 sentences with no waste; the 'what it explains' clause comes first and the usage trigger second. Slightly dense enumeration of topics, but everything 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?

With an output schema present, return-value explanation is unnecessary, and the single optional parameter defaulting to 'all' is documented in the schema. The description covers purpose, static nature, and usage timing; only explicit sibling routing 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 description coverage is 100% and the enum's own description already explains every topic value ('interpretation: score meaning; models: publishing history...'). The description adds no per-topic semantics beyond that, so the schema carries the load and a 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?

The description states a specific verb and resource: it explains EPSS interpretation, model publishing dates, coverage limits, and prioritization policy, and calls itself a 'static reference'. That is clearly differentiated in spirit from the data-returning siblings (epss_get_scores, epss_get_timeseries, epss_prioritize_cves, epss_query_threshold), though none are named explicitly.

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?

'Use this static reference before interpreting missing scores, score movement or probability versus percentile thresholds' gives a concrete trigger condition tied to the sibling tools' outputs. It stops short of stating when not to use it (e.g. 'do not call for live scores'), which keeps it from 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?

Annotations only cover read-only/idempotent/open-world safety, so the description carries the real behavioral burden and does so: thresholds are policy conventions not FIRST guidance, missing severity falls into epssOnly, missing EPSS stays unscored, batching is capped at 500 unique entries with a byte budget returning whole entries, and deferred vs withheld entries are distinguished. That is exactly the context an agent needs to avoid misinterpreting results.

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 policy defaults and percentile guidance are front-loaded, and nearly every sentence adds operational information. It is dense and uses internal result-field names (epssOnly, withheldCves, nextBatchOffset) without defining them in prose, which slightly raises reading cost for a first-time caller.

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 paged, policy-driven scoring tool with a full output schema, the description covers what the output schema cannot: threshold conventions, unknown-severity/unknown-EPSS disposition, batch limits, and the exact resume procedure. An agent could call and correctly paginate this tool from the description alone.

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 would be 3; the description adds meaning beyond the schema by restating the default policy values in operational terms and by explaining the batchOffset resume contract (resubmit original cves, score date, and same thresholds). It does not elaborate on threshold syntax beyond what the schema already documents, so it stays short of a 5.

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 a specific verb and resource: assign remediation tiers using EPSS data plus caller-supplied CVSS severity. It clearly separates this from siblings like epss_query_threshold or epss_get_scores by framing it as a policy/tiering operation rather than a raw lookup, and it scopes the input set (up to 500 unique entries from batchOffset).

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?

It gives concrete selection guidance: defaults are severity >= 7 and EPSS >= 0.10, and 'select percentile explicitly for population rank' tells the agent when to deviate. The resume protocol is spelled out precisely. It does not, however, name a sibling tool as the alternative for simpler queries, so routing between tools is left partly to inference.

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 past the readOnly/idempotent/openWorld annotations: it discloses the 65536-byte response cap, the budgetLimited and withheldCount fields, nextOffset pointing at the first withheld match, empty pages under year filtering, and the broad-query nature of candidateTotal. That is exactly the operational context an agent cannot get from 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?

Front-loads purpose and the filter-intersection rule, then moves to paging and caveats. Dense and every sentence carries information, though the phrasing is packed tightly enough to require a re-read.

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 9-parameter filtered/paginated tool with an output schema, it covers the pieces the schema cannot: pagination continuation protocol, byte-budget truncation signals, and the year-filter empty-page trap. An agent can call and page it correctly from the description alone.

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 earns more by explaining cross-parameter behavior the schema cannot: filters intersect, at least one is required, limit clamping above 10000 happens before year filtering, and offset must come from nextOffset.

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: 'Discover CVEs' with inclusive EPSS/percentile bounds, year, or recency filters. It is clearly a threshold-based discovery tool, distinguishable from get_scores/timeseries/prioritize siblings by implication, though it never names them explicitly.

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 real selection rule — filters intersect and at least one is required — plus continuation instructions. But it never says when to reach for this instead of epss_get_scores or epss_prioritize_cves, leaving the sibling choice to inference.

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