Parlel

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

With no annotations, the description must carry the burden of transparency. It clarifies the operation is for one published agent and lists returned components (brief, schedule, recent findings with sources). However, it does not mention failure behavior for invalid/non-published slugs, potential access restrictions, or whether 'recent findings' are filtered in any way.

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?

The description is one tight sentence, front-loads the core action ('One published agent by slug'), then lists key return contents. It is concise and scannable, though it could add a phrase explaining where to get a slug without losing brevity.

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?

The tool is simple with one required parameterhol. The description covers the resource identifier and the main return elementsaren. But it doesn't address what happens if the slug doesn't exist or agent isn't published, and doesn't explicitly direct users to search_agents for discovery. Given the low complexityyb, this is adequate but not thorough.

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% and the sole parameter 'slug' has no schema description. The description only mentions 'by slug' without explaining what a slug is, how to find one, or its expected format. This does not meaningfully compensate for the undocumented 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 says 'One published agent by slug: its brief, schedule and recent findings with sources.' This is a specific verb+resource pairing (get one agent by slug) and lists the included fields, making the purpose clear. It does not explicitly contrast itself with search_agents or other get_* siblings, but the singular 'one... by slug' strongly implies a direct lookup.

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 identifies the identifier (slug) and singular nature, but gives no guidance on when to use this tool versus search_agents, how to obtain a valid slug, or any preconditions (e.g., agent must be published). There is no exclusion or explicit alternative.

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?

With no annotations, the description carries the burden of behavioral disclosure. It does disclose that open roles are included inline, which is useful. However, it doesn't state what happens if the handle doesn't exist, whether the company is returned with all fields, or any rate-limit/auth behavior. The description is accurate but minimal.

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?

The description is a single, front-loaded sentence that states the resource, the key, and the notable return detail. Every word earns its place; there is no fluff or repetition of 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?

The tool has one required parameter, an output schema, and no nested objects, so complexity is low. The description covers the core purpose and the inline roles detail. However, with no annotations and no usage guidance, an agent might not know error behavior or how this differs from search_companies. It's adequate but not complete.

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 compensate. It does clarify that 'handle' is the lookup key for the company, which adds meaning beyond the bare schema property name. However, it doesn't explain the format of the handle (e.g., slug, ID, URL-encoded name) or provide examples, so the compensation is partial.

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 'One company by handle, with its open roles inline' clearly identifies the resource (company), the lookup key (handle), and the return shape (open roles inline). It distinguishes itself from siblings like get_agent, get_job, and get_person by naming the specific resource, though it doesn't explicitly contrast with search_companies.

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 this is the direct-fetch tool for a single company by handle, while search_companies would be the alternative for querying/filtering. However, it doesn't explicitly state when to use this vs. search_companies, nor does it mention any prerequisites or context for when the inline roles are included.

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?

With no annotations, the description carries the behavioral disclosure burden. It adds non-obvious context that closed roles are still retrievable and advises reading the status field, which is valuable. However, it does not mention error cases, response shape beyond the output schema, or permissions – gaps that a simple read tool could reasonably disclose.

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?

The description is two sentences with no filler: it front-loads the primary action, lists what is included, and adds the closed-roles nuance efficiently. Every clause contributes to the agent's understanding.

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 low-complexity get-by-id tool with an output schema, the description covers the essential facts: what is returned, that closed roles are included, and that status should be read. It could explicitly state that this is for when an ID is already known, but the siblings and the title make that sufficiently inferable.

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 schema describes role_id only as a string with title 'Role Id' and 0% description coverage, so the description's 'by id' clarifies that this parameter is the role identifier. That is minimal added meaning; no format, example, or further semantics are provided, but the single parameter makes the intent reasonably clear.

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 the tool retrieves a single role by id and enumerates the returned content (full description, skills, pay, hiring company). It distinguishes itself from the search_*/get_* siblings by its singular, id-based focus.

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 provides clear context: it returns one role by id and works for closed roles too, signaling when this direct lookup is appropriate. It does not explicitly name alternatives like search_jobs for discovery, but the contrast is implicit and the closed-role note is a meaningful usage 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?

With no annotations, the description carries the transparency burden. It discloses that only published profiles are returned and enumerates the returned fields, which is useful behavioral context. It does not discuss error cases, authentication, or rate limits, but for a simple read operation this is adequate.

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?

The description is a single, well-structured sentence that front-loads the core behavior and uses a colon to compactly list the returned profile components. There is no redundant or filler content.

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 details are covered elsewhere. The description adequately explains the lookup mechanism and scope for a simple fetch-one tool. Minor gaps remain around handling of nonexistent or unpublished handles, but they do not materially impair correct invocation.

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 compensate. It clarifies that 'handle' is the lookup key, but adds no format, uniqueness, or case-sensitivity details. Since there is only one self-explanatory parameter, this is acceptable but not richly documented.

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 identifies the operation as retrieving a single profile by handle and lists the profile contents returned (headline, bio, work history, etc.). The title 'Read one profile' plus 'One published profile by handle' distinguishes it from the search_people and other get_* siblings.

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 'One published profile by handle' gives clear context: use this when you have a specific handle and want that profile's details. It does not explicitly state when to prefer search_people or other alternatives, but the access pattern is obvious enough to guide selection.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains what watch agents are, that results include previews, and that there's no text filtering. It also documents the sort parameter values. However, it doesn't disclose pagination behavior (cursor usage), rate limits, or what happens when the list is exhausted. The description adds useful context but leaves some behavioral aspects undocumented.

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?

The description is compact and front-loaded. The first sentence defines the resource and its purpose, the second clarifies the lack of filtering, and the third documents the sort parameter. Every sentence earns its place with no 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?

The tool has an output schema, so return values are already documented. The description covers the core semantics: what watch agents are, that previews are included, no text filter, and sort options. It could be more complete by explaining pagination behavior (cursor/limit) and how this differs from sibling search tools, but for a simple browse tool with an output schema, it's largely 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 description coverage is 0%, so the description must compensate. It does explain the sort parameter ('sort is recent or popular') and implies limit and cursor through 'walk the list' (suggesting pagination). However, it doesn't explain the semantics of limit (max results per page) or cursor (pagination token) beyond what the schema already shows. The description adds some value for sort but not for limit/cursor.

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 the tool's purpose: browsing published watch agents, which are standing searches people run against the open web, with a preview of findings. It distinguishes itself from sibling search tools by explicitly noting 'No text filter; walk the list,' making it clear this is a browse-all operation rather than a filtered 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 description provides clear context for when to use this tool: when you want to browse published watch agents without filtering. It explicitly states 'No text filter; walk the list,' which implies it's not for targeted searches. However, it doesn't explicitly name alternatives like search_companies or search_jobs for filtered searches, so it falls slightly short of a 5.

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?

With no annotations, the description carries the full behavioral burden. It discloses meaningful behavior: only companies with a published page are returned, `industry` is an exact label, and `hiring=true` narrows results. However, it does not mention pagination, result ordering, whether filters combine, or how `cursor` and `limit` behave, leaving gaps 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?

The description is three tight sentences, front-loads the core scope, and uses backticks for code identifiers. Every sentence adds either filter semantics or a useful return-field note; there is no filler or repetition of the 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?

The definition covers the essential search behavior and mentions the notable output field `open_role_count`, and an output schema exists to document return values. Still, for a 7-parameter search tool with no annotations, it would benefit from at least a mention of pagination (`cursor`, `limit`) and how the filters combine.

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 compensate. It does add meaning for `q`, `industry`, and `hiring`, explaining match semantics and exactness. However, it omits `size`, `location`, `limit`, and `cursor`, although those are partly self-explanatory from the schema's types, defaults, and enum values.

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 identifies the resource (companies with a published page) and the search behavior: `q` matches name, tagline, or industry, `industry` is an exact label, and `hiring=true` filters by open roles. It is specific enough to distinguish this from sibling search tools like search_people or search_jobs, and the 'Each item' phrasing signals a list-returning 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?

There is no explicit guidance on when to use this tool versus alternatives like get_company or search_people. The filter semantics are described, but the description does not state when a user should prefer this tool, when they should use get_company for a single entity, or any exclusions.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals the return shape ({items, next_cursor}), the matching behavior (q matches title only), and the ordering (newest first). It also mentions the presence of `role_url` in each item, which is useful for citations. However, details like pagination mechanics, response size limits, or error handling are omitted, so it's not fully transparent but substantially informative.

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 with zero filler. The first establishes the resource and ordering; the second packs the matching semantics, filters, and return format. Front-loaded and efficient, every clause contributes value.

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 tool with 6 parameters, an output schema, and no annotations, the description gives the essential behavioral contract (return shape, matching scope, filters). It does not explain the units for `comp_min` or the exact meaning of 'working arrangement' relative to the `remote` enum, but these are minor gaps given the schema's enum values provide some clarity. Overall, a well-rounded description that leaves few critical unknowns.

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 compensate. It explains `q` (title match), `seniority` (seniority filter), `comp_min` (pay floor), and `remote` indirectly via 'working arrangement'. The `limit` and `cursor` are not individually described but are standard pagination parameters inferable from the return structure. This is a solid recovery given zero schema descriptions, though a couple of parameters rely on inference.

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 the tool lists 'Open roles on Parlel' with a specific ordering ('newest first'), and explicitly notes that `q` matches the TITLE only. This gives a precise verb+resource and distinguishes it from sibling tools like search_agents, search_people, and search_companies, which target different entity types. The purpose is unmistakable.

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 usage for finding job postings on Parlel and mentions available filters (working arrangement, seniority, pay floor). It does not explicitly state when not to use it or name alternatives, but the sibling set clearly indicates that this is the go-to tool for open roles. The filtering hints help an agent decide how to narrow results, but explicit exclusion guidance is absent.

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?

With no annotations, the description carries the full behavioral burden and does this well: it scopes results to published profiles, defines what q matches and explicitly excludes skills/bio, explains that skills are exact AND-ed tags, distinguishes based_in from location, and states contact details are never returned. It omits pagination and ordering, but these are secondary.

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, information-dense sentences with zero filler. The key scope ('Published profiles') is front-loaded, and every sentence adds value about matching semantics or output limitations.

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?

The description covers the ambiguous search semantics, filter interactions, and privacy constraints, while the output schema handles return shape. It does not explain how non-q filters combine or how pagination works, but for a 10-optional-parameter tool with no annotations this is still reasonably complete.

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 compensate for the schema. It does for q, skills, based_in, and location with precise behavioral details, but leaves limit, cursor, remote, comp_max, seniority, and open_to_work unexplained. Those names and the schema's enum/default values give some context, so the gap is moderate.

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 and resource: searching published people profiles, with person-specific attributes like name, headline, company, role, and work history. This makes it easy to distinguish from sibling tools like search_agents or search_jobs, though it does not name any 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?

The description provides no explicit when-to-use guidance or alternatives. It implies a public-profile people search and warns that contact details are never returned, but it never tells the agent when to choose this tool over search_agents, search_companies, or search_jobs.

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