Work Insiders

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful disclosure beyond that: the data source, the fact that each match reports vendor confirmation, an evidence link, and the sync direction — return-shape information that matters because no output schema exists.

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?

Three dense sentences with no filler, and the primary purpose is front-loaded. The middle sentence ('With a tool given as well, it checks that one pair') is slightly clunky in construction, but every sentence carries distinct information.

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 6-parameter read tool with no output schema, the description covers purpose, both modes, data source and per-match return fields. Pagination and category semantics are left to the schema descriptions, which is acceptable given their 83% coverage, though a brief note on result paging would make it fully self-sufficient.

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 83%, but the description adds the key semantic the schema cannot express: the interaction between 'ats' alone (list mode) and 'ats' plus 'tool' (single-pair check). That dual-mode behavior is the most important thing an agent must understand about this parameter set.

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 names the exact resource (ATS compatibility data for Bullhorn, Greenhouse, Lever, Workday, JobAdder, etc.) and discloses both operating modes: list tools for an ATS, or check one ATS+tool pair. An agent can distinguish it from sibling tools like search_tools or compare_tools purely from the text.

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 clearly implies when the optional 'tool' parameter triggers the pair-check mode, and mentions that the category list comes from workinsiders_list_categories. However, it names no alternative sibling tool and gives no explicit when-not-to-use guidance, leaving the routing decision implicit.

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=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds the notable fact that results are aggregate and that some data may be absent (prices can be hidden or free), which is useful. It does not describe output structure, caching, or freshness, keeping it at a baseline-plus level.

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?

A single dense sentence, front-loaded with the core question ('what a category costs and who leads it') followed by the returned fields. Every listed item is meaningful and wastes no words. It reads slightly like a data dump, but the leading clause frames it well.

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 one-parameter, read-only aggregate tool with annotations covering safety and a fully documented schema, the description is largely complete. It explains the aggregation concept and data caveats (hidden prices, free plans), though it omits any hint of result ordering limits or freshness.

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 single category parameter is fully documented in the schema, including format examples and a pointer to list_categories. The description adds no new parameter-level meaning beyond the schema. 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?

States a specific resource (category) and enumerates exactly what is returned (tool count, median price, MCP server counts, editor picks, cheapest prices, intro). It is clearly distinguishable from siblings like get_tool or compare_tools. It lacks an explicit verb, but the enumerated payload makes the purpose concrete.

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: it answers aggregate pricing/leadership questions for one category. The schema links to workinsiders_list_categories for valid slugs, which is a useful entry point. However, it never states when to use this vs. search_tools or compare_tools, so the agent must infer that this is for high-level category summaries rather than per-tool lookups.

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, non-destructive and closed-world, so the safety profile is covered. The description adds the set of comparison dimensions, which is helpful context, but says nothing about behavior when a tool name is unknown or how results are ordered.

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?

A single compact sentence with the scope ('2 to 4 named tools') front-loaded before the field list. Dense but not padded; every element earns its place, though the field enumeration could be seen as listing output content in the description.

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 one-parameter, read-only tool with no output schema, the description effectively doubles as a return-value summary by listing the compared dimensions. Nothing critical is missing, though it omits error/invalid-name handling.

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 single parameter is fully documented with min/max items. The phrase '2 to 4 named tools' merely restates the schema's minItems/maxItems constraints, adding no syntax or format detail beyond the schema.

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 (compare) and resource (tools) and enumerates exactly what is compared: pricing, free plan, MCP, API, best for, watch-outs, bottom line, Capterra rating. An agent can distinguish this instantly from siblings like get_tool or find_alternatives.

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?

'2 to 4 named tools' implies the precondition that the caller must already know which tools to compare, which is useful context. However, it never states when to prefer this over get_tool (single lookup) or find_alternatives, so usage is only implied.

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 a safe, idempotent, closed-world read. Beyond that, the description discloses the composition and ordering of results: Work Insiders' write-up picks with stated reasons first, then other same-category tools. It does not cover behavior when the named tool is unknown or absent from the dataset.

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 with the core behavior front-loaded and no filler. The trailing filter clause is partly a restatement of schema parameters, which is the only mild redundancy.

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 correctly explains what the returned list contains and how it is ordered (write-up picks with reasons, then same-category tools). For a five-parameter read tool with rich annotations, only the not-found case and result count are left implicit, which the schema's default/max limit partly handles.

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 80%, so most parameters are already documented in the schema, including the detailed pricing normalization rules. The description names the filter dimensions (MCP, free plan, price) at a high level but adds no syntax or edge-case meaning beyond the schema, and omits `limit` entirely. Baseline 3 applies.

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: given one named tool, return alternatives to it. It is clearly distinguishable from siblings like get_tool, search_tools and compare_tools by the 'alternatives to one named tool' framing plus the result ordering. It stops short of explicitly naming which sibling to use instead in adjacent cases.

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 description (use this when you have a single tool and want substitutes), and the filter set hints at narrowing scenarios. However, there is no explicit when-not condition or pointer to a competing sibling such as search_tools for open-ended discovery.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description doesn't need to restate them. It adds useful scoping context by introducing a new behavioral fact: the price includes the date it was checked, implying time-sensitivity. However it says nothing about depth limits, throttling, or what happens on a missing tool name. Adequate but not rich.

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 long enumerative sentence followed by a short routing sentence — front-loaded and waste-free, but the field list is dense and could have been trimmed to the most decision-relevant fields. Still, every clause carries identifying information.

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 single-parameter read tool with no output schema, the description usefully enumerates the returned profile sections and points to the search sibling. It lacks guidance on handling a not-found tool or partial profiles, a minor gap against an otherwise complete definition.

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 slightly beyond by framing the parameter's role as identifying 'one named tool', reinforcing the single-tool lookup semantics, and the schema itself gives accepted forms (name, slug, URL) with examples.

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 (returns) and resource (full profile of one named tool), then enumerates the exact fields returned. It also explicitly distinguishes itself from the sibling workinsiders_search_tools, so an agent can route correctly without opening schemas.

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 closing sentence names the sibling alternative (workinsiders_search_tools) and the condition that selects it (finding tools by need or filter), implying this tool is for retrieving detail on a known tool. That is explicit when-to-use-this-vs-alternative guidance.

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 the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false, no destructive effects), so the bar is lower. The description adds the useful detail that this returns the full category set (not a filtered subset), but does not describe pagination, ordering, or result size.

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?

A single front-loaded sentence that states the operation, the resource, the scope of results, and the fields returned. No filler or redundancy.

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 zero parameters, full schema coverage, and annotations declaring the safety profile, the description supplies what remains: what the list contains and the shape of each item. It could be stronger with a note on how this differs from category_overview, but 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?

The tool takes zero parameters, so there is no parameter semantics to document; baseline 4 applies. The description compensates by describing the return shape (slug, tool count, page link), which is the only information an agent needs to use the result.

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 (Lists) and resource (Work Insiders categories), and enumerates example category types plus the returned fields (slug, tool count, page link). It does not distinguish itself from the sibling workinsiders_category_overview, which an agent might reasonably confuse for similar category-listing behavior.

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?

No when-to-use guidance. The description never mentions when this tool should be called instead of siblings like category_overview or search_tools, leaving the agent to infer that this is the entry point for browsing the directory.

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 and closed-world behavior, so the bar is low. The description still adds useful context beyond them: page size cap of 25 results, the fields each result carries (starting price, flags, Work Insiders page link), and pagination through offset/limit.

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, front-loaded with the core verb and scope, then the return shape and the hand-off to get_tool. No filler or restated title text.

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 an 11-parameter search with no output schema, the description summarizes the return payload and page size and points to siblings for drill-down and category enumeration, which is enough to call it correctly. It stops short of describing sort semantics or empty-result behavior, both of which remain schema-side.

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 91%, so the schema already documents nearly every parameter, including the price normalization rules and enum default. The description only re-enumerates the filter dimensions and the 25-per-page cap, adding little syntax or meaning beyond the structured fields — baseline 3 applies.

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 — searching the Work Insiders directory of 1,000+ tools — and names the filter axes. It explicitly distinguishes itself from the sibling workinsiders_get_tool, which handles single-tool detail, so an agent can route 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?

Gives clear context (free text plus filters) and routes to workinsiders_get_tool for full detail on one result, with workinsiders_list_categories referenced for category slugs. It never states a when-not-to-use condition or contrasts with compare_tools/find_alternatives, so it stops short of an explicit routing rule set.

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