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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context — and it does, spelling out exactly what computed values come back and that arbitrary version notations are normalized. It stays silent on failure behavior for unknown products/versions and on any auth or rate constraints.

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 clause, with return fields and input tolerance following in priority order. The trailing example list is long but each item demonstrates a distinct notation family, so it earns most of its space.

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 no output schema and no annotation hints about returns, the description correctly compensates by naming the returned fields. The remaining gap is discoverability: nothing tells the agent that `product` values come from list_products, nor what happens when a product or version is unrecognized.

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 genuinely extends the schema: it adds `v18.19.0`-style prefixes, `net472`, `4.8`, and `lts/hydrogen` codenames that the schema's own examples do not cover, telling the agent normalization is tolerant. The `product` and `date` parameters get no description-level treatment, keeping it below 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?

Specific verb + resource ('Checks one product version') plus a precise enumeration of the result fields (support status, end dates, days remaining/overdue, latest patch, newest cycle, recommended upgrade). The singular 'one product version' scope counters scan_project and get_cycles by implication, though no sibling is named outright.

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 rather than stated: it is clearly a point-lookup check, and the accepted-input list signals real-world version strings. There is no explicit when-to-use, when-not, or pointer to list_products for discovering valid product ids, so an agent must infer routing from the sibling names.

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 establish read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuine context beyond that: result ordering ('newest first') and the fact that status and days-remaining are computed relative to a supplied evaluation date, which tells the agent the output is time-sensitive even though the resource is static.

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?

One front-loaded sentence: verb and resource first, then the returned field list. Every clause names a concrete output field or ordering rule; nothing is wasted or restated from the title.

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 no output schema, the description carries the full burden of explaining returns, and it does so thoroughly by enumerating release date, LTS flag, both support end dates, computed status, days remaining, and latest patch. Minor gaps remain around error behavior for unknown products and the up-to-500 limit ceiling, but nothing essential to calling 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%, with the date, limit and product parameters each documented in the schema, so the baseline is 3. The description only adds the 'newest first' ordering that implicitly ties limit to recency; it adds nothing about product id resolution or limit interaction beyond what the schema already says.

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 every release cycle of a product') and enumerates exactly what comes back, so an agent knows precisely what this fetches. It never names or differentiates itself from the related sibling check_version, so the agent must infer which one answers a support-status 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?

There is no explicit when-to-use or when-not-to-use statement, and no reference to the alternatives in the sibling list (check_version, scan_project). Usage is only implied by the resource being fetched and by the 'newest first' ordering, which is enough to make the basic case clear but leaves the check_version boundary unresolved.

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, non-destructive and closed-world, so the safety profile is fully covered. The description adds that this is a static snapshot and that ids feed downstream tools, but says nothing about result truncation, ordering, or what a response entry looks like.

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 tight sentences, no filler. The identity of the resource comes first, the payoff (ids for other tools) and filtering behavior follow in a logical reading order.

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 simple read-only list tool with full annotation coverage and a fully documented schema, this is nearly sufficient; the role of the returned ids is the key missing context and it is supplied. Only the absence of any note on result volume or paging behavior keeps it off a 5, and limit/default are covered in the schema anyway.

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 each parameter carries a precise description, so the schema does the heavy lifting. The description only adds that the two filters combine ("and/or"), which is a marginal gain over 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?

"Lists the products in the endoflife.date snapshot" gives a specific verb and resource, then enumerates the domain (runtimes, frameworks, databases, operating systems) so the scope is unmistakable. The clause about returning ids "for use in the other tools" positions it distinctly against get_cycles/check_version/scan_project, which all consume those ids.

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 phrase "for use in the other tools" plus "Filter by a search text and/or category" makes the intended discovery-first workflow and narrowing options clear. It stops short of explicitly saying when not to use it or which sibling to reach for next, so an agent must infer the ordering.

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/non-destructive/non-open-world, so the safety profile is covered. The description adds real value beyond that: the deterministic ordering (most urgent first) and the presence of a summary paragraph, which matter for interpreting results. It stops short of saying what happens with unrecognized file names or with files beyond the 200-item cap.

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 and output shape are stated first, then the file list — good front-loading. The enumerated format whitelist is long but it is operationally necessary for the agent to know what to send, so it earns its space; only the trailing 'and more' softens an otherwise tight list.

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 no output schema present, the description carries the burden of describing returns — and it does, including ranking order and an extra summary field. Combined with the supported-file list and the contents-not-paths warning, an agent has everything needed to call this 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 baseline is 3; the description earns an extra point by supplying the supported-filename whitelist and by clarifying that a path's name (not its content alone) decides how the file is interpreted. That is meaningfully more than the schema's `path`/`content` field docs.

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 (reads) plus resource (project files) plus precisely stated output (detected runtimes/frameworks with support status, sorted most urgent first, plus a summary paragraph). Nothing here overlaps with siblings like check_version or get_cycles, so an agent can route to it unambiguously.

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 front-loads the key invocation constraint — pass file *contents*, not disk paths — which pre-empts the most likely misuse. It also conveys the use case via the supported-file whitelist, but it never names an alternative tool or states when *not* to use this one.

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