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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantive context: salary units (million Toman per month, from a survey), how to read the histogram (share of participants per pay band), the time window of the growth figure, and the presence of a `search` payload carrying jv_search arguments for open ads. Remaining gaps are minor (no size/pagination of the response), and nothing conflicts with 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?

Front-loaded with the core purpose, then progressively adds output detail; nearly every sentence carries information. The trailing `search` sentence is loosely attached and slightly hard to place, costing a bit of crispness.

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 two-parameter read-only lookup with no output schema, the description does the needed work by enumerating return contents (salary histogram, growth, satisfaction, entry steps, neighbouring careers, ad-search arguments). The only soft spot is the under-specified `search` value and how the caller is meant to use it.

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%, including the enum and default for city_size, so the schema already carries parameter meaning. The description adds unit semantics for the salary output rather than for inputs, and the sentence about `search` holding jv_search arguments is ambiguous about whether that is a returned field or an input, which is not clarified anywhere in 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?

States a specific verb and resource ('Get ... career-guide profile of one job title') and enumerates the payload (salary distribution, demand, duties, skills, path). The clause 'Use after jv_careers' plus 'one job title' separates it cleanly from the jv_careers listing tool.

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?

Explicit sequencing guidance ('Use after jv_careers') tells the agent this is the detail call for a single career. No exclusion is offered against overlapping siblings such as jv_pay_stats, so an agent wanting only salary data has no stated rule for choosing between them.

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 read-only, idempotent, non-destructive, open-world profile, so the description is free to add provenance: the salary figures come from Jobvision's own survey and are therefore not limited to ads that show pay, unlike jv_pay_stats. It also gives the unit (million Toman per month). It does not say how ties are broken or what happens when limit exceeds the ~100 title pool, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose leads, then the concrete use case, then the compare/contrast with a sibling and the hand-off to jv_career. Three sentences, no filler, and the parenthetical about survey provenance is load-bearing rather than decorative.

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 still conveys what comes back (a ranked list of job titles on the chosen dimension) and three fully documented parameters. It does not describe the shape of a ranked row (e.g. whether satisfaction score or ad counts are included per entry), which is the main residual gap for a listing 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; the description earns above that by explaining what the salary sort actually means (median salary from a survey, in million Toman per month) and by implying the filter matches partial job titles through its example. It still leaves the interplay between query and limit unaddressed.

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 specific verb (rank) and resource (~100 job titles in Jobvision's career guide) plus the three ranking dimensions. It explicitly separates this tool from jv_pay_stats and points to jv_career for per-job detail, so an agent can place it among siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names two concrete user intents ('which jobs pay the most', 'what does an accountant earn') that map to this tool, and states explicitly which tool to call instead for duties/skills/distribution (jv_career) and how it differs from jv_pay_stats. That is when-to-use plus alternatives, not mere implication.

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, openWorldHint and non-destructive, so safety is covered. The description adds real behavioral context beyond them: results come back in the site's company ranking, and 'rating is out of 5 (absent when nobody rated it)' warns that the field may be missing. It does not discuss pagination limits or total result counts, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose and default ordering, then routing, then a compact glossary of rank and rating. Nothing is repeated from the input schema and there is 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?

With no output schema, the description correctly fills the gap by defining the two returned fields an agent is likely to misread (rank as overall position, rating out of 5 and sometimes absent). For a nine-parameter search tool it covers the essentials, though it says nothing about paging behavior or how many results to expect overall.

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 one of the nine parameters is already documented, including the enum for size, defaults, and the jv_options id lookups. The description adds no parameter-level detail beyond what the schema states, so the baseline 3 applies; its extra semantics concern rank/rating output rather than inputs.

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 ('Find companies on Jobvision') plus the default ordering ('best rated first, the site's company ranking'). It explicitly separates itself from jv_search ('Jobvision's job search cannot' look up a company by name), so an agent can distinguish it from siblings 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?

Gives two concrete use cases: name lookup and browsing top employers 'by industry, city, size or score'. It also names the follow-up tools (jv_company for profile and open ads, jv_interviews for interview experiences), and the input schema points to jv_options for benefit/industry ids.

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 read-only, idempotent, open-world, non-destructive, so the description is free to add value and does: it enumerates the returned profile fields and states the ads come back "newest first" as job cards. It stops short of covering failure modes (unknown id, rate limits), which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the action and result, then the input source, then the disambiguation pointers to siblings. 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?

There is no output schema, so the description carries the return-shape burden and discharges it by listing the profile attributes (size, ownership, industries, city, founding year, website, benefits, rating, rank, counts) and the embedded ad cards. For a two-parameter read tool with full annotation coverage, nothing material 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 baseline is 3, but the description adds cross-tool meaning the schema lacks: it tells the agent where company_id can be sourced from (jv_search / jv_job) and that open_jobs governs the embedded ad list returned "newest first." That is genuine semantics beyond the field descriptions.

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?

"Get an employer's profile and its currently open job ads" names a specific verb (get) and two concrete resources (profile, open ads), which immediately separates it from jv_search or jv_job in the sibling list.

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 states the required input provenance ("a company id from jv_search or jv_job") and explicitly routes two adjacent needs elsewhere: jv_companies for name-to-id lookup and jv_interviews for interview reports. Both an when-to-use condition and named alternatives are present.

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real value beyond them: passing an `article` route switches the tool from listing to full-text reading, and the result body is flagged as third-party content rather than instructions (a useful injection warning). It stops short of describing pagination, limits, or what a listing entry contains.

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, all load-bearing: purpose, use case, single-item mode, sibling routing, plus a safety note. The scoping statement is front-loaded and nothing is repeated unnecessarily.

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 three-parameter read-only tool with full annotation coverage, the description covers selection, alternatives, and the article mode well. The remaining gap is the absence of an output schema combined with no statement of what a listing entry actually contains (beyond the `article` field), which an agent must discover by calling.

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 `limit`, `sector`, and `article` are already fully documented, including the enum values and the 1–16 bound. The description adds only the behavioral consequence of `article` (returns the announcement in full) which the schema also states, so it is baseline rather than additive.

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 ('List Jobvision's recruitment announcements') plus a bounded domain (public-sector hiring calls: exam dates, conditions, deadlines). It explicitly contrasts itself with sibling jv_search, so an agent can choose between them without opening either 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 positive when-to-use ('state and semi-state hiring calls that are not ordinary ads'), a negative/alternative rule ('For the actual open ads of the sector call jv_search with government=<sector>'), and a mode instruction for reading a single item. Alternatives and exclusions are both explicit.

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 readOnly/idempotent/openWorld safety, and the description adds meaningful context beyond them: the split between an aggregate `summary` (score and difficulty out of 5, typical duration, common steps) and individual `reports`, an explicit zero-report edge case, and a warning that report text is user-written and not instructions. That last point is valuable prompt-injection guidance an agent cannot infer from structured 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?

The purpose and return-shape summary are front-loaded in the first two clauses, followed by a usage sentence and a response-shape sentence. Every sentence carries distinct information with no restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description compensates by explaining the two top-level fields (`summary` and `reports`), their contents, and the empty-result case. Combined with a fully documented input schema and safety annotations, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so page, show, sort, limit and company_id are all documented in the schema, including enum meanings and example company id. The description reinforces the `show` split by mentioning questions, but adds no format or interaction detail beyond what the schema already provides, so 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?

The opening sentence names a specific verb ('Get what candidates report') and a precise resource ('interviewing at a company') and enumerates the content returned: scores, difficulty, process, questions. That scope is clearly distinct from jv_company (company facts) and jv_job (postings) among the 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?

It explicitly says to use this 'after jv_company or jv_companies to judge how a company treats candidates', giving clear sequencing and intent. It stops short of stating when not to use it or naming an alternative source for interview data, so it lacks full exclusion 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 declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds genuine value beyond them by enumerating what is returned (skills, software, conditions, benefits, pay, location, dates, employer summary) and flagging that pay is in million Toman per month and "often hidden" — a real caveat an agent should expect. It stops short of noting auth or rate-limit behavior, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with purpose, then return contents, then a follow-up routing hint. No filler, no restatement of the title, and each 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?

There is no output schema, so the description must describe returns — and it does so in detail, including units and the hidden-pay caveat. For a one-parameter read tool with full annotation coverage, nothing an agent needs 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?

Schema description coverage is 100% and the single job_id param is already documented with an example value in the schema. The description only reinforces provenance ("Use after jv_search or jv_similar_jobs"), which is marginally additive. Baseline 3 is correct when the schema does the heavy lifting.

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?

"Get the full text and requirements of one Jobvision job ad" names a specific verb (get), a specific resource (one job ad), and its scope (single ad, full detail). This clearly separates it from list-style siblings like jv_search and jv_similar_jobs without requiring the schema to be opened.

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 after jv_search or jv_similar_jobs" explicitly states the upstream tools that produce the job_id, and "Call jv_company with company.id" routes the agent onward for a related need. Alternatives and sequencing are stated rather than inferred, which is the top bar for this dimension.

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, openWorld and non-destructive, so the safety profile needs no restating. The description adds genuinely new behavioral context: the three result kinds, the 'all-cities-of-...' slug convention for provinces, and the fact that Tehran areas include diagonal ones like tehran-shomalgharbi, which shapes how an agent should interpret and reuse returned values.

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 the enumeration in a second line. Every clause carries usable information — no restatement of the title or annotations.

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 lookup with no output schema, the description adequately covers what comes back (names and slugs of provinces, cities, areas) and the slug formats. It does not say whether results are a flat list or grouped, or how many are returned, which is the only notable gap given the absence of an output schema.

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 'query' parameter already documents that it takes part of a name and that empty lists provinces. The description adds only indirect meaning by enumerating the kinds being matched; it offers no extra detail on matching behavior (prefix vs substring) beyond the schema's 'Part of a ... name'.

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 ('Find the province, city or Tehran area names and slugs') and ties the output directly to a named sibling: the values 'jv_search's city filter accepts'. An agent can distinguish this lookup helper from jv_search without opening either 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 an explicit trigger condition: 'Use when a city name does not resolve', which tells the agent this is a fallback resolution step before calling jv_search. It stops short of stating when not to call it (e.g. when the query is a company or job title), so it is clear but not fully exclusive.

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?

Goes well beyond the readOnly/idempotent/openWorld annotations: discloses caching (two minutes), request fan-out per split (77 for category, 32 for province, at most 10 otherwise), the max_requests cap, and how truncation surfaces as groups_checked below groups_total. It also warns of two counting quirks — pay bands only count ads showing pay, and overlapping work types can make groups sum above the total — which materially affect interpretation of results.

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?

Purpose and example questions are front-loaded in the first two sentences, followed by operational caveats in descending importance. Dense but every clause carries distinct information — request counts, caching, truncation semantics, counting caveats — 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?

With no output schema, the description does the necessary work: it states that whole-site totals accompany every call and that groups_checked/groups_total signal truncation. It stops short of describing the exact response shape (e.g., group label fields per split), but an agent has enough to call and interpret it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real semantics: keyword, city and category all narrow the counted set, and max_requests caps fan-out with a visible truncated-split signal. It stops short of clarifying interactions between keyword and category (intersection vs. union) or how `top` interacts with `by`.

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?

Opens with a specific verb+resource and scope: 'Count open Jobvision ads per category, province, work type, seniority, experience, pay band or age.' It also explicitly separates itself from siblings by ending with 'use jv_search with the same filters to read the ads', so the agent knows this tool aggregates while jv_search retrieves ads.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete triggering questions ('which categories hire most in Shiraz', 'how many python ads per province') and names the follow-up alternative (jv_search) with the condition that selects it. It also points to jv_locations and jv_options('categories') for identifier lookup, covering the main navigation decisions.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so safety is covered. The description adds value beyond them by disclosing the shape of the returned values (ids, slugs, Persian and English names), which the annotations cannot express and which tells the agent what it can do with the result.

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 primary purpose front-loaded and no filler. The final parenthetical about jv_search taking friendly names is slightly elliptical, but the description still reads quickly.

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-enum lookup tool with full annotation coverage and no output schema, the definition covers purpose, value-to-consumer mapping, and return shape. The only gap is that it doesn't say whether the lists are exhaustive or whether the fixed-choice lists (work_types, seniority, etc.) should be read directly or simply trusted.

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 `kind` enum is fully enumerated with short glosses, so the baseline of 3 applies. The description does add the mapping from `category`/`industry`/`benefit` values to their use in jv_search, but it adds no detail for work_types, seniority, experience, salary_ranges, or posted_within beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource — 'List the values of one Jobvision filter' — and states what comes back: ids and slugs with Persian and English names. That is a distinct job from every sibling (jv_search, jv_locations, jv_suggest), so an agent can route here without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete when-to-choose guidance by tying each enum value to its consumer: 'categories for jv_search's category slug, industries for `industry`, benefits for `benefit` (ids)'. It stops short of saying the tool should be called before jv_search to resolve friendly names to ids, and the closing sentence about 'the other lists' is loose about which values those are.

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 read-only/idempotent/non-destructive profile, and the description adds substantive behavior: sampling up to 300 of the newest matching ads, aggregating only ads that show a pay range, and computing median of range midpoints plus quartiles and extremes. The caveat that this is advertised pay rather than actual earnings, and that small ads_with_pay counts make results rough, is exactly the kind of limitation an agent needs before quoting numbers.

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?

Purpose, example, methodology, caveat, and alternative are ordered sensibly with no filler sentences. Slightly dense in the middle with nested parentheticals, but nothing 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?

There is no output schema, so the description carries the return-value burden and does so: it names the statistics returned (median, quartiles, extremes) and the ads_with_pay field an agent needs to judge reliability. For a six-parameter, all-optional aggregation tool, nothing material 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 100%, so every filter is already documented, including slug formats and the cross-references to jv_locations and jv_options. The description only implicitly characterizes the filters as 'newest matching ads' and adds no per-parameter meaning beyond the schema, so 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: 'Estimate pay for a role from the salaries open Jobvision ads advertise', with units given (million Toman per month). It explicitly contrasts itself with jv_search, so an agent can distinguish it from siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete when-to-use example ('how much does a python developer earn in Isfahan') and names the alternative for the other intent: use jv_search with sort=salary to see the actual ads. It also points at share_with_pay for the coverage caveat, which routes the agent rather than leaving it 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 cover read-only, idempotent and open-world, so the bar is lower. Beyond them the description discloses that results are paginated to one page of compact cards, that 'applied' echoes only the filters Jobvision recognised (a real silent-drop warning), and that most ads hide pay. It does not mention rate limits or what a card contains, but the added context is substantive.

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?

Purpose and the 'use this first' directive are front-loaded, and the follow-up routing is compressed into one sentence. A few clauses (pay explanation) sit slightly awkwardly after the routing, but there is 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 an 18-parameter, all-optional search with no output schema, the description covers the essentials: what comes back, pagination, filter-echo behaviour, and the sibling chain for depth. It would be stronger if it sketched the fields of a compact job card, since there is no output schema to do that.

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 every parameter is already documented with examples and enums. The description adds only the pay unit (million Toman per month) and the prevalence of hidden pay, which is useful interpretation but not new parameter syntax. 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 and resource ('Search Jobvision job ads') plus the return shape ('one page of compact job cards'). That return-shape clause also separates it from jv_job, jv_company and jv_similar_jobs, which are named as follow-ups.

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 this first for any job hunt' gives an explicit entry point, and the id-then-follow-up chain (jv_job for full text, jv_company for employer, jv_similar_jobs for related) tells the agent what to do after a hit. No explicit when-not-to-use case is stated, so it stops 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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real context beyond them: results are Jobvision-curated similarity and come back as the same compact cards as jv_search, which tells the agent how to consume the output. It omits anything about result count, ordering or pagination.

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, with the core action first and the usage cue second. Nothing is repeated from the title or 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?

For a one-parameter read tool with rich annotations and no output schema, this is close to sufficient: purpose, sequencing and return-card format are all covered. Only the volume of returned cards is left unknown, which an agent might need to plan a widening search.

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 job_id parameter is fully documented in the schema with range and format. The description adds only a minor nuance by suggesting the id can follow jv_job, while the schema cites jv_search as the source, so 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 and resource: lists job ads Jobvision deems similar to a given ad. It is clearly differentiated from jv_job (single ad lookup) and jv_search (broad query), so an agent can pick it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use after jv_job to widen a search around a good match" gives an explicit trigger and names the preceding tool. It implies jv_search is the alternative for a fresh search but never states a when-not condition or that the input id must already be known-good.

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 open-world behavior, so the safety profile needs no restating. The description adds genuine behavioral context beyond them: results are ordered by usage frequency and the intent is autocomplete-style prefix matching. Return shape and result count are not covered, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero waste; the core behavior and result ordering come first, followed by the usage note pointing at jv_search.

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 autocomplete tool with full schema coverage and annotations covering safety, the description supplies what the structured fields cannot: prefix intent and usage ordering. It doesn't describe the returned suggestions' shape, though that is minor for this complexity.

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 schema already documents the single keyword parameter with an example ('pyth or حساب'). The description adds no syntax or format detail beyond that, so the baseline of 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 ('Autocomplete job titles') plus the ordering behavior ('most used first'), and explicitly contrasts with jv_search, so an agent can distinguish it from siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear use case with a named alternative: use this to discover the wording ads actually use before calling jv_search. There are no explicit when-not conditions, but the sequencing guidance is unambiguous.

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