StackVersus: verified SaaS limits & pricing

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

Annotations already cover read-only, idempotent, non-destructive, closed-world, but the description goes well beyond: missing ids are returned in `missing` and are never an error, cross-dataset products are permitted, checked dates are attached, and fees are deliberately not aggregated. These are behavioral traits no annotation could convey.

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 what the tool is, then enumerates the return shape, then the edge cases and pricing caveat. Dense but every clause carries information an agent would otherwise have to discover by calling it.

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?

There is no output schema, yet the description names every returned field (compared, missing, note, tools and per-record contents). Combined with the fee-separation caveat and the 2–6 limit, an agent has everything needed to call 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?

With one parameter and 100% schema coverage, the schema already documents the array and its 2–6 bounds. The description adds provenance for the values (list_tools or search_limits output) and confirms a plain product name is acceptable, which is more than the schema states.

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 (read-only compact comparison) plus explicit scope: 2 to 6 products. The multi-product framing inherently distinguishes it from get_tool (single record) and search_limits, so an agent can select it without inspecting the 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 context for invocation: products may come from different datasets, and ids come from list_tools or search_limits. It also warns that platform fees and pass-through costs stay as separate rows and must be summed by the caller. It stops short of explicitly excluding the single-product case (get_tool) or naming a when-not-to-use condition.

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 the description goes well beyond them: resolution rules (case-insensitive, exact match wins, otherwise substring), explicit error behavior that returns candidate ids on ambiguity, currency (USD), and the critical `published: false` caveat that values are vendor wording and must never be estimated from. That last point is a genuine behavioral warning not derivable from any structured field.

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 is one dense, front-loaded block with no filler — return shape first, then matching rules, then error behavior, then the pricing caveat. The middle enumeration of record fields is long but each field is load-bearing given there is no output schema. Slightly heavy as a single paragraph, but nothing is redundant.

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?

There is no output schema, so the description carries the full burden of describing `matches` and `records` — and it does, down to nested `plans`, `rates`, `free`, `overage`, `gotchas`, `sources` and `checked`. Combined with the ambiguity/error path and the `published` caveat, an agent has everything needed to call this correctly 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?

With 100% schema coverage the baseline is 3, and the description adds real semantics for `tool_id`: case-insensitive, exact-match-wins-then-substring resolution, with concrete example values. It does not explain the `dataset` parameter's disambiguation role in the description text (the schema handles it), which keeps it just 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 opens with a specific verb and resource: 'Read-only full verified record for one product,' and the return-shape enumeration makes it unmistakable versus siblings like list_tools (enumeration) or compare_tools (multi-product comparison). An agent can distinguish this from all five siblings without opening a 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?

Usage is implied rather than stated: it says to match 'by id (e.g. "claude", "cursor"...)' or by name, and that ambiguous/unknown names error with candidate lists, which tells the agent how to recover. But there is no explicit when-to-use-this-vs-alternatives statement (e.g. 'use list_tools first to discover ids', or 'use compare_tools for multiple products'); list_tools only appears in the schema, not the description.

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 read-only, idempotent, non-destructive, but the description adds substantial context beyond them: the 60-row cap, newest-first ordering, the 30-day default window, that only real moves are returned by default, what include_wording unlocks, and the dataset coverage limitation. That is exactly the behavioral detail an agent needs.

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 purpose and dataset scope, then the return shape, then usage. It is dense and the long enumeration of returned fields is somewhat list-heavy, but every element carries information about what an agent will get back.

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, so the description's enumeration of returned fields (since, count, changelog, changes with date/tool/plan/field/old/new/source/method/note/page) fills that gap. Combined with the dataset limitation and default filtering, an agent has everything needed 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; the description adds value by explaining the default look-back window (30 days) and by characterizing include_wording as re-verification rows for wording-only or first-recorded values, which is richer than the schema's wording.

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 ('read-only dated change log') and immediately scopes it to the ai-plans dataset, noting other datasets have no history. It also distinguishes itself from siblings by naming get_tool as the tool to cross-check figures against.

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 usage examples ('what changed in the Claude plans this month') and an explicit cross-check scenario with get_tool. It clarifies the default filter (real moves only) and how include_wording broadens scope, but does not explicitly state when not to use it versus compare_tools or search_limits.

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 non-destructive, so the safety profile is covered. The description adds concrete operational facts: no auth, no pagination, whole catalog in one call, and it enumerates the current dataset count and topics so an agent knows what to expect back.

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 assertion and the return shape before the usage routing, with no filler. The enumeration of all nine dataset topics is the one place it runs long, though it does double as discovery aid given there is no output schema.

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, yet the description documents every returned field (id, title, kind, tools, plans, updated, page, json, generated) and explains that id is what other tools accept as dataset. It also states record count and call behavior, leaving no gap an agent would need to probe.

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, so there is nothing to disambiguate and the baseline is high. The description correctly reinforces 'No parameters' rather than leaving the empty schema to speak for itself.

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 ('Read-only catalog of the datasets on this server') plus explicit scope. It distinguishes itself from the sibling that handles per-dataset drill-down by naming list_tools directly.

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 explicit routing guidance: 'Use it once to learn dataset ids; use list_tools to see the products inside one dataset.' That names both the when and the alternative, so an agent can decide without inspecting schemas.

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, and no side effects, yet the description reinforces scale and behavior beyond the annotations: ~100 rows by default, dataset scoping, no pagination, no auth, and that prices/limits are absent. This adds real behavioral context, though it repeats the read-only/no-side-effects framing already in annotations, 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 purpose and routing before detailing return fields. It is dense and every clause is useful, though the return-field enumeration is slightly lengthy; still efficient overall.

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, so the description carries the return-value burden and does so fully: it lists returned fields (id, name, vendor, dataset, checked, plans, page) and states what is absent (prices, limits). Combined with routing and scale info, an agent has everything needed 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% and the enum is fully documented, so baseline is 3. The description goes beyond the schema by explaining the default behavior of omitting dataset (all products, ~100 rows) versus scoping to one, adding semantic meaning to the optional parameter.

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 ('Read-only list of the products (vendors) covered') and explicitly distinguishes purpose from siblings by naming get_tool and compare_tools as the id-lookup consumers. An agent can identify this as a catalog/ID-lookup tool without opening the 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 explicit when-to-use ('to look up ids before calling get_tool or compare_tools') and when-not-to-use ('When the user already names a product, skip this and call get_tool or search_limits directly'). Both the positive and negative routing conditions are spelled out with named alternatives.

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 safety (readOnlyHint, idempotentHint, destructiveHint=false), and the description goes well beyond them: whole-word case-insensitive matching, the strict-then-relaxed matching rule, the `relaxed` flag, ranking by match quality, a 20/50 row cap with no pagination, and empty rows returned instead of an error. This is unusually rich behavioral disclosure for a search 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-loaded with purpose and the example queries, followed by return shape then matching semantics. It is dense and every sentence carries information, but it is delivered as one long unstructured paragraph, making the return-field list harder to scan than a short bulleted shape.

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?

There is no output schema, and the description compensates fully by enumerating every returned field (`query`, `relaxed`, `total`, `shown`, `rows` and each row's type/tool/value/unit/quote/sourceUrl/checked/page). Combined with the empty-result behavior, an agent has everything needed to call this and interpret the response.

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 meaning the schema does not: what 'relaxed' means for `query` matching, the whole-word case-insensitivity rule, no operators, and that `limit` is a ranked quality cut (max 50, default 20) with no pagination. That is genuine value over the enum/text 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 concrete verb and resource: 'Read-only keyword search across every plan, limit, rate, free tier, overage rule and gotcha in all datasets.' It explicitly distinguishes itself from siblings by naming list_tools and get_tool as follow-ups, so an agent can tell it apart from compare_tools/list_changes without opening a 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?

Explicitly declares itself the 'Best first call' and gives three concrete example questions that should route here. It also names the fallback path ('then try list_tools to find the product id and call get_tool') for the empty-result case, which is a real when-to-use/when-not distinction.

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