HireHouse Jobs

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

Annotations already establish read-only, idempotent, closed-world, non-destructive behavior, so the description's remaining job is to add context — and it does, disclosing that only public listings are compared, the 2-5 cardinality limit, and the exact return contents (listing data, description excerpt, application URL). That is meaningful added value 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?

A single sentence with the comparison scope front-loaded and zero wasted words; every clause (cardinality, selector, return contents) 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?

There is no output schema, so the description compensates by enumerating what comes back (listing data, excerpt, application URL). For a one-parameter read-only comparison tool, nothing needed for correct invocation 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 0%, so the description must carry the burden, and it largely does: 'by job ID' identifies jobIds and 'two to five' restates the minItems/maxItems bounds. It does not call out the UUID format constraint, but that gap is minor for a single array 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?

The description names a specific verb (Compare) and resource (public HireHouse roles), plus the scope (two to five, by job ID) and the payload returned. It implicitly separates itself from single-role tools like get_job, but never names a sibling, so it stops short of the explicit differentiation a 5 requires.

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 only implied: an agent can infer this is for side-by-side evaluation of several roles rather than fetching one. There is no explicit when-to-use/when-not statement and no pointer to get_job or search_jobs as alternatives or 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful scope detail that only public data and the application URL are returned, but says nothing about not-found behavior or whether the returned URL is authenticated/session-bound.

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 names the verb, the cardinality, and the three things returned. Every clause earns its place with no filler.

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 single-record fetch with no output schema, the description tells the agent what it will receive and the scope (public details). Error/not-found handling is the only real omission, which is minor for a tool whose annotations already establish a safe, idempotent read.

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 there is only one parameter, jobId, whose UUID format is enforced in the schema and whose meaning is largely self-evident from the name and the phrase 'for one job'. The description adds no format or sourcing detail beyond that, so it neither fully compensates nor misleads.

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 (Get) and resource (one job) and even enumerates the payload: public details, full description, and the HireHouse portal application URL. 'For one job' usefully signals a single-item fetch as opposed to the list-oriented sibling search_jobs, though no sibling is 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?

Usage is only implied: the phrase 'for one job' suggests this is the single-record lookup you use once you already have a jobId, contrasting with search_jobs/show_jobs/compare_jobs. No explicit when-to-use, when-not-to-use, or alternative is named.

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 is not obliged to restate it. It adds genuine value beyond the annotations: the AND semantics of `query` ('every word must match'), the related-results fallback with match: "related", and the public-listings-only constraint.

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 tight sentences, front-loaded with scope and matching semantics before filters and constraints. No filler, though the final sentence ('Results are public listings only') partially restates the opening 'publicly listed' qualifier.

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 usefully hints at the return shape via the match: "related" field, and covers matching behavior, scope, and available filters. Missing pieces are minor: pagination behavior for a page param capped at 100, and no indication of result ordering defaults beyond the sort enum.

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 63%, so several parameters (page, sort, workMode) are undocumented in the schema. The description names the filter families (location, work mode, compensation, featured, recency, sort) mapping them loosely to parameters, and clarifies `query` matching semantics beyond the schema. That is adequate but not a full compensation for the coverage 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?

States a specific verb and resource with scope qualifiers: 'Search currently active, reviewed, publicly listed Hirehouse roles.' An agent knows this is a job search returning listings. It does not, however, distinguish itself from siblings show_jobs, get_job, or compare_jobs, so the sibling-differentiation credit is not earned.

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 scope statement ('publicly listed roles only') and the filter list, but there is no explicit when-to-use guidance and no mention of when to prefer show_jobs, get_job, or compare_jobs. The fallback rule for empty results is described, which is useful behavioral context rather than usage routing.

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 covered. The description adds genuinely new behavioral context — the rendering as interactive cards, the 1-10 bound, and that each card links out to the application page — but says nothing about ordering, error behavior for invalid/missing IDs, or what happens for non-public roles.

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 cardinality and output form front-loaded; nothing is wasted or 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?

With no output schema, the description does the right thing by describing the return as linked interactive cards. It is close to sufficient for a simple single-argument display tool, with only edge-case behavior left unspecified.

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 0%, so the description must carry the load, and it only identifies the parameter as job IDs and restates the 1-10 cardinality already encoded in minItems/maxItems. It does not explain what happens to unknown or duplicate IDs.

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 (Display) and resource (one to ten public HireHouse roles by job ID) along with the output form (interactive job cards). It is distinguishable from get_job and compare_jobs by the card rendering, though it never names the siblings 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?

The phrase 'by job ID' implies the caller must already hold job IDs (i.e., use search_jobs first), which is a useful implicit condition. However, there is no explicit when-to-use guidance or statement of when to prefer get_job or compare_jobs instead.

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