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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by stating the data is 'public' and that fields are returned 'when available', warning the agent about optional/absent 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?

A single front-loaded sentence with no filler; purpose and the returned field set are both delivered immediately.

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 lookup tool with an output schema already documenting return shape and with safety hints in annotations, the description is nearly complete; only explicit guidance on choosing this over search_companies 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 reported as 0%, so the description must carry the param burden, and it does: it explains the single 'id' can be a stable ID or a slug, matching the schema's oneOf integer/string union and adding the semantic that the ID is stable.

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 (Get) and resource (company) scoped to a single entity looked up by stable ID or slug, and enumerates the returned fields. This implicitly and clearly distinguishes it from the sibling search_companies, which handles multi-entity search.

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 'by stable ID or slug' implies a direct-lookup use case versus searching, but there is no explicit when-to-use guidance, no mention of when to prefer search_companies, and no stated prerequisites. 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.

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

Annotations already declare the safe read-only, non-destructive, closed-world profile, so the bar is lower. The description adds real behavioral context beyond them: results are 'compact' (lightweight payloads) and the cursor is opaque and must be passed unchanged with the same companyId, which tells the agent how pagination must be driven.

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 short sentences, zero filler, with the core purpose front-loaded and the cursor caveat immediately after. Every clause carries information the 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?

With an output schema present, return-value detail is unnecessary, and annotations cover the safety profile; the description supplies the remaining critical operational detail (cursor reuse with the same companyId). It does not clarify pagination termination or what 'compact' omits, leaving a small gap.

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 beyond the schema's 'Opaque continuation cursor' by specifying it must be passed unchanged and paired with the same companyId. It says nothing extra about limit or companyId, so it is not a full 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?

States a specific verb ('Get'), resource ('public jobs') and scope ('for one published company'), which clearly separates it from company-level siblings like get_company or search_companies. It does not explicitly distinguish itself from get_jobs, search_jobs, or get_similar_jobs, so it stops short of a 5.

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?

'for one published company' implies the required precondition (you need a companyId for a published company), but there is no explicit when-to-use versus search_jobs/get_jobs guidance and no stated exclusions. 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.

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

Annotations already declare the tool as read-only, non-destructive, and non-open-world, so the description needn't repeat safety. The description adds that it fetches 'public description and details' of a 'visible job', implying access controls, but doesn't specify error cases or rate limits. With annotations covering basics, a 3 is appropriate.

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, zero waste, and front-loaded with purpose followed by usage condition. Every word 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?

Given the tool's simplicity (one parameter, output schema present), the description provides all necessary context: what it does, when to use it, and the scope. Annotations cover safety, and output schema handles return values, so nothing critical 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%, so the single parameter 'id' is fully described. The description doesn't add format or semantics beyond 'by ID', which is redundant with the schema. Baseline 3 is correct when schema is complete.

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 clearly states a specific verb ('Fetch') and resource ('full public description and details of one visible job by ID'). It distinguishes from 'search_jobs' (bulk search) and 'get_jobs' (probably listing), allowing an agent to select the correct tool 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?

Explicitly states when to use this tool: 'Use after search_jobs when the complete vacancy is needed.' This provides both the trigger (post-search) and the condition (full details required). Sibling tools are indirectly referenced, giving clear 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 cover the safety profile (readOnly, non-destructive, closed-world), yet the description adds genuinely useful behavior: it preserves original full job objects and a JSON array in content.text, and requires no authentication. The geo-eligibility rule (country, parent region, globally available) is non-obvious semantics not present in the 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?

Four short sentences, front-loaded with what the tool is, then output format, then the sibling alternative, then the geo caveat. Dense and waste-free, though the telegraphic phrasing ("Geo means candidate eligibility") reads more like notes than polished documentation.

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 values need not be described, and the description still adds the legacy content.text layout detail. The main residual gap is behavior around count/pagination and how the several filter parameters interact, which neither the schema nor the description resolves.

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 88%, so the baseline is 3; the description exceeds it by clarifying that geo means candidate eligibility rather than a plain location filter, which the schema only labels as "Public text." It does not disambiguate the overlapping search/keyword/tag/category/industry parameters, leaving that gap.

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 identifies the resource and scope clearly ("Legacy-compatible public jobs feed") and explicitly contrasts itself with search_jobs, so an agent can distinguish it from the sibling that returns compact results. It stops short of a crisp verb+object statement like "retrieve full job objects," but the resource and its legacy nature are unambiguous.

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 search_jobs for compact results and more filters" gives an explicit alternative plus the condition that selects it, and "Legacy-compatible" implies this is the choice when old-format payloads are needed. It does not spell out a full when-not-to-use case, but the routing guidance is concrete.

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, destructiveHint=false and openWorldHint=false, so safety and scope are covered structurally. The description adds the genuinely useful behavioral trait that the result set is 'deterministic' and 'small', but says nothing about ordering, default limit, or behavior for an unknown slug.

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 zero filler, front-loaded on the verb and resource, with the scoping rule (shared career category) immediately following. Nothing to trim.

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-value explanation is unnecessary, and both parameters are fully documented in the schema. What remains missing is minor: the default for limit and the failure mode for an unrecognized role slug.

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% ('Career role slug.' and 'Maximum related roles.' with min/max constraints), so the schema fully documents both parameters. The description adds no syntax, format, or default-value detail beyond that, which is the expected baseline when the schema does the work.

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 ('Get') and resource ('roles'), and explains the derivation rule: roles sharing the same Jobicy career category as the requested role. This differentiates it in substance from get_similar_jobs and get_role, though it never names those siblings explicitly, so an agent must infer the distinction.

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 mechanism described (fetch related roles by shared career category), and 'small deterministic set' hints at when this is preferable to a similarity-based tool. However, no explicit when-to-use, when-not-to-use, or named alternative is given.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description's help. The description adds the useful qualifier that the guide is 'public' (no auth implied), but the enumerated sections largely restate what the output schema already conveys.

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 sentence, front-loaded with the verb and resource, with no filler. Every clause either identifies the resource or scopes the input.

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 full annotation coverage and an output schema, the description is nearly sufficient. The only weakness is that the listed content sections duplicate what the output schema already defines, and no edge case (e.g. invalid or unknown slug) is mentioned.

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 single parameter is described as 'Career role slug.', so the baseline would be 3. The description goes slightly further by tying the slug to the '/careers/' URL path, which tells the agent where the identifier originates and what format to expect.

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 ('Get') and resource ('Jobicy career role guide') with the lookup key ('/careers/ slug'), which separates it from sibling tools like get_job, get_company and get_related_roles. It stops short of explicitly naming which sibling to use for adjacent needs, but the resource is unambiguous.

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 implies the tool is used when you already hold a /careers/ slug, but gives no when-to-use conditions, no prerequisites, and no reference to alternatives such as get_related_roles or get_taxonomies. Guidance is left entirely 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?

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real behavioral context beyond them: results are limited to public jobs, ranking is deterministic, and scores are relevance weights rather than probabilities — a distinction that prevents misinterpreting the output.

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 with the purpose front-loaded and no filler. The weight enumeration is terse and information-dense, though bare numbers ('type 2, level 2') are slightly cryptic without units.

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-value explanation is unnecessary, and the description covers the ranking semantics that the schema cannot. Only the absence of explicit routing guidance against siblings leaves a minor gap.

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 both parameters (jobId, limit) are documented in the schema, so the baseline is 3. The description hints at result sizing ('small set') but adds no format or range detail beyond what the schema already supplies.

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: 'Recommend a small set of public jobs related to one job.' The 'related to one job' scoping and 'public' qualifier distinguish it from get_jobs/search_jobs, though it never names a sibling 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?

Usage is implied by 'related to one job' — an agent can infer this is for finding neighbors of a known job — but there is no explicit when-to-use guidance, no mention of when to prefer search_jobs or get_related_roles instead, and no stated prerequisites.

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 readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description adds real context by noting it is legacy-compatible and where the payload lands ('original JSON in content.text'), though it omits auth requirements, rate limits and whether the returned set is paginated.

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 short sentences with the purpose front-loaded before the usage condition and the return-location detail. Slightly awkward phrasing around 'original JSON in content.text', but no sentence is wasted.

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 lookup with an output schema, the core need is met: what it returns, how to get it, and when to call it. The missing piece is disambiguation from resolve_taxonomy/list_taxonomies, which an agent has no way to resolve 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?

Only one parameter exists and it is a two-value enum whose values (locations/industries) are fully self-describing. The description reinforces the split by framing the tool as a 'location or industry lookup', so semantic coverage is effectively complete despite 0% schema description coverage.

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 gives a clear verb-implied resource ('location or industry lookup') and matches the enum values in the schema, so an agent knows exactly what data comes back. It differentiates itself from search_jobs, but says nothing about how it differs from its closest siblings, resolve_taxonomy and list_taxonomies, which is the overlap that matters most.

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 an explicit when-to-use condition ('when a filter slug is uncertain') paired with a when-not/alternative ('obvious values can go directly to search_jobs'), which is more than most definitions offer. The guidance is undercut by not addressing resolve_taxonomy or list_taxonomies, the siblings an agent is most likely to confuse it with.

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, non-destructive, closed-world), and the description adds a genuine scope limitation: no job or company counts are returned. That negative disclosure helps the agent know when this tool is insufficient.

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, no filler, and the core purpose is front-loaded ahead of the exclusion note. Every clause 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 values need not be explained, and the single enum param plus the count-exclusion note make the tool callable. The one missing piece is routing versus the sibling taxonomy 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 0%, but the single parameter is a self-documenting enum whose four values the description restates verbatim. Nothing about format, defaults, or combining values is added, so this is baseline adequate rather than helpful.

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 (List) and resource (public filter slugs and labels) and enumerates the four taxonomies covered. It does not distinguish itself from the sibling get_taxonomies, so it stops short of a 5.

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 when-to-use guidance and no mention of alternatives such as get_taxonomies or resolve_taxonomy, which look like close substitutes. Usage is only implied by the word 'filter'.

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 readOnly, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine behavioral context beyond that: low-confidence matches return candidate slugs without auto-selecting one, which tells the agent to expect an ambiguous/plural result and to make the final choice itself.

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, zero waste. Purpose is front-loaded and the failure-mode caveat follows immediately, so an agent gets the essentials in the first clause.

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 values needn't be explained, yet the description still covers the one return behavior that matters (candidates on low confidence). For a two-parameter read-only resolver, nothing an agent needs to invoke 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 50%, and the description only loosely maps to the two parameters ('location or industry name' corresponds to query/type). The schema already enumerates type and describes query as 'Name, abbreviation or alias', so the description adds little syntax or format detail; 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 verb (Resolve) and resource (location or industry name to a Jobicy slug), so an agent knows exactly what transformation it performs. It doesn't name sibling tools like list_taxonomies or get_taxonomies, so it falls short of explicit sibling differentiation, but the 'when unsure of a slug' framing implicitly separates it from the list/get taxonomy 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?

'Use when unsure of a slug' gives a clear selection condition that distinguishes it from direct taxonomy lookups. There is no explicit 'when not to use' or named alternative, but for a simple resolution helper the trigger condition is unambiguous.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a hard cap of 10 results and the absence of a cursor or overall count, which tells the agent this cannot be paginated or used for counting.

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 short sentences, front-loaded with the purpose, then the required-criterion constraint, then the result limitation. Nothing is padded, though the result-cap sentence partially overlaps with the output schema and could be trimmed.

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 detail is not needed, and the description covers scope, the result cap, and the absence of pagination. Its one weak spot is the mismatch with the schema's empty required list, which could lead an agent to call it with no criteria at all.

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 every parameter is already documented in the schema, making the baseline 3 appropriate. The description restates the three search facets but adds no syntax, matching, or slug-format guidance beyond what the schema provides.

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+resource (find public companies) and enumerates the three searchable facets (name, industry, headquarters text), which matches the query/industry/geo parameters. It implicitly separates this search tool from the sibling get_company/get_company_jobs lookups, but never names them, so differentiation relies on the reader's 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?

"A search criterion is required" tells the agent a precondition, and "this is not a company directory export" rules out a bulk-enumeration use case. However, it never says when to prefer this over get_company or get_taxonomies, and the claim that a criterion is required conflicts with the schema's empty required list, leaving the agent to guess.

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/destructiveHint/openWorldHint, so the safety profile is covered. The description adds non-obvious behavioral context: geo resolves via candidate eligibility including parent regions and global jobs, cursors are opaque, and jobCount counts only the current page. This is meaningful disclosure beyond the 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?

Five short, front-loaded sentences, each carrying distinct information (scope, geo semantics, routing, cursor rule, page counting) with no filler or repetition of structured fields.

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 values need not be described, and the description covers the tricky parts an agent must know: geo eligibility semantics, cursor handling, routing to resolve_taxonomy, and page-scoped jobCount. Nothing essential is missing for a 12-param search tool.

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 baseline is 3, but the description adds real meaning the schema lacks: geo is not a plain slug match but an eligibility model (parent regions, global jobs), and cursor must be passed unchanged with identical filters. These additions lift it above baseline.

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 gives a clear verb+resource ('Search public remote jobs') and adds a distinguishing scope note ('compact results, without full descriptions'), which signals it differs from a full-detail fetch. It does not explicitly name the closest sibling (get_jobs), so differentiation is implied rather than stated.

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 an explicit routing rule: 'Call directly when filters are clear; use resolve_taxonomy for uncertain slugs,' naming the alternative and the condition that selects it. It also supplies pagination usage guidance ('pass nextCursor unchanged with identical filters'), leaving little to inference.

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