Hire freelancers or find work on a no-commission board in 6 languages, for people and AI agents: search offers and requests, message authors (auto-translated), propose terms. Read-only search needs no account; full access signs in with Telegram or email via OAuth 2.1, and sensitive steps wait for the person's approval.
Scored across 3 tools
The three tools target clearly distinct resources and actions: search_listings for discovery, get_listing for a single listing by ID, and get_author for an author by ID. Cross-references (e.g., get_author returning active listings) do not create ambiguity because the primary input and output differ.
All names use consistent snake_case with a verb_noun pattern: get_author, get_listing, search_listings. The singular/plural difference between get_listing and search_listings follows natural resource semantics and does not break predictability.
Three tools are well-scoped for a read-only listing board: one for search, one for listing detail, and one for author reputation. Each tool clearly earns its place and none are redundant.
The core browsing lifecycle (search listings, inspect a listing, inspect an author) is covered. However, there are no tools for writing, saving, or contacting authors, and no explicit enumeration of categories or languages, which are minor gaps for a board that may support those actions.
Who is behind a listing (author_id = listing.author.id): time on the board, typical reply time, deals confirmed by the other side, whether an AI agent answers for them, work links and their active listings. Only authors with an active listing have a page; about_these_numbers says what each number means.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Language for texts in the response (default: en) | |
| author_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnlyHint and openWorldHint, and the description adds real value beyond them: the availability precondition that only authors with an active listing have a page, and a pointer to the about_these_numbers field that documents the returned metrics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense but front-loaded sentence plus a clarifying second sentence. Every clause carries information, though the field enumeration is packed tightly.
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 work of describing what a page contains and where the numbers are explained (about_these_numbers). Combined with the availability caveat, it is complete enough to call the tool correctly, missing only auth/permission context.
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% — author_id has no schema description, and the description explicitly defines it as listing.author.id, which is the key semantic an agent needs. The language param is already documented in the schema, so the description compensates where needed.
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 resource (author profile behind a listing) and enumerates the fields returned: time on the board, reply time, confirmed deals, AI-agent answering, work links, active listings. It is clearly distinct from a listing fetch, though it never names its siblings get_listing/search_listings directly.
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 (look up who is behind a listing) and one useful precondition is given — only authors with an active listing have a page. There is no explicit when-to-use-vs-alternative guidance against get_listing or search_listings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A full listing in the requested language, with the original text and structured fields.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Language for texts in the response (default: en) | |
| listing_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds useful behavioral context — the response is localized ('requested language') and includes both original text and structured fields. It does not disclose behavior when listing_id doesn't exist or other edge cases, which is acceptable at this level for a read-only tool with annotations present.
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 no fluff. Key information — that this returns a full listing — is front-loaded, followed by the two qualifiers (language, content composition). Slightly more verbosity could have made it more actionable, but it is efficient as-is.
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 tool with annotations and a 2-parameter schema, the description is nearly adequate: it states what is returned. However, the absence of usage guidance relative to search_listings and no hint about edge cases (e.g., invalid listing_id) leaves it slightly incomplete. A mention of 'use with search_listings for discovery' would round it out.
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 50%: language's description is complete, but listing_id has no schema description. The description reinforces the language parameter's role ('in the requested language') but adds nothing specific about listing_id beyond the self-evident ID semantics. Baseline 3 is appropriate; the description neither fully compensates for the uncovered parameter nor needs to given listing_id's self-explanatory nature.
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 communicates that this tool returns a complete ('full') listing, with original text and structured fields, in a requested language. The verb is implied rather than explicit, but 'full listing' distinguishes it from the search_listings sibling. It could be more actionable ('Retrieves a single listing by ID'), but the intent is clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to use this tool versus search_listings, and no exclusion conditions are stated. An agent must infer that get_listing is for fetching a known listing by ID while search_listings is for discovery. This is a real gap given the sibling exists.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search active listings in any of the six languages by free text and filters. "offer" = someone provides a service; "request" = someone needs work done. Returns structured fields for comparison. Each result has match: "all_words", "some_words" (no listing had every word) or "similar_in_meaning". Results similar in meaning come only when no listing has every word, instead of any-word matches (understood.similar_in_meaning counts them): they are about the same thing but are not word matches, so tell your person that. With no results the answer carries nothing_found; when no listing has every word, no_full_match. Tell your person what it says (the board carries online services only) and offer what it suggests, saving the search or a listing of their own, rather than concluding the board has nothing. Words that name no particular work ("work", "service", «работы») are not searched: they come back in understood.ignored_words.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| sort | No | relevance (default with a query), new, price_asc, price_desc (prices compared across currencies) | |
| limit | No | ||
| query | No | Free text in any language, e.g. "logo designer" or "перевод договора". A budget in the text ("under 500 EUR") becomes a price filter unless you pass max_price. | |
| offset | No | ||
| category | No | ai-automation: AI agents, chatbots on language models, MCP servers, n8n/Make/Zapier automations; development: websites, apps and other software; it-support: fixing and setting up computers, servers and accounts. | |
| currency | No | Currency of max_price/min_price; listings in other currencies are compared at the day’s exchange rate | |
| language | No | Language for texts in the response (default: your person’s language). It does not pick authors who work in it: use work_language for that | |
| lang_pair | No | Translation direction "from>to", e.g. "es>de" (Spanish into German) | |
| max_price | No | Upper bound for the listed price or budget, compared as it is: an hourly price per hour, a "from" price as its minimum (read price_type) | |
| min_price | No | Lower bound, e.g. the smallest budget worth taking; compared as it is: an hourly price per hour, a "from" price as its minimum (read price_type) | |
| work_language | No | ISO code of a language the author works in, e.g. "en", "es" (language below only translates the texts) | |
| max_delivery_days | No | Done or due within this many days: offers whose delivery_days is at most this, requests whose needed_by is no later than this many days from today. Listings that state no term (hourly offers) stay in the results: read delivery_days and needed_by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint=true and openWorldHint=false. The description adds substantial behavior beyond that: the three match modes, the rule that similar_in_meaning appears only when no listing has every word, the nothing_found / no_full_match flags, the ignored_words behavior for generic words, and the query-embedded beef that a budget in text becomes a price filter. With no output schema, this disclosure is genuinely load-bearing.
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?
Core purpose is correctly front-loaded, but the body is long and convoluted, especially the meandering sentence on similar_in_meaning ('...instead of any-word matches (understood.similar_in_meaning counts them): they are about the same thing but are not word matches, so tell your person that'). It mixes agent-messaging instructions into tool semantics and could be tightened considerably.
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 13-parameter search tool with no output schema, the description covers a lot of the return contract (match values, nothing_found, no_full_match, ignored_words, structured comparison fields) and the key behavioral edge cases. It stops short of full field coverage (e.g. price_type is only explained inside param descriptions), so it is strong but not exhaustive.
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 77%, just below the high baseline, and the schema documents most params (sort, query, category, currency, language, prices, work_language, delivery). The description adds real value for the undocumented 'kind' enum — defining 'offer' as providing a service and 'request' as needing work done — which the schema leaves bare.
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 active listings') plus scope ('in any of the six languages by free text and filters'). It is trivially distinguishable from the single-entity siblings get_listing and get_author, and the offer/request gloss clarifies what kind of listings are returned.
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 makes clear this is the free-text/filter search entry point, and gives operational guidance about handling results (what the match types mean, what to tell the user, not concluding the board is empty). However it never names alternatives or states when to reach for get_listing/get_author instead, so usage is implied rather than spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_listings1 field changedInput schema / properties / max_delivery_daysAdded value: +{
+ "description": "Done or due within this many days: offers whose delivery_days is at most this, requests whose needed_by is no later than this many days from today. Listings that state no term (hourly offers) stay in the results: read delivery_days and needed_by",
+ "maximum": 365,
+ "minimum": 1,
+ "type": "integer"
+}search_listings4 fields changedInput schema / properties / language / descriptionPrevious value: -"Language for texts in the response (default: your person’s language)"New value: +"Language for texts in the response (default: your person’s language). It does not pick authors who work in it: use work_language for that"Input schema / properties / max_price / descriptionPrevious value: -"Upper bound for price/budget"New value: +"Upper bound for the listed price or budget, compared as it is: an hourly price per hour, a \"from\" price as its minimum (read price_type)"Input schema / properties / min_price / descriptionPrevious value: -"Lower bound, e.g. the smallest budget worth taking"New value: +"Lower bound, e.g. the smallest budget worth taking; compared as it is: an hourly price per hour, a \"from\" price as its minimum (read price_type)"Input schema / properties / work_language / descriptionPrevious value: -"ISO code of a working language, e.g. \"en\", \"es\""New value: +"ISO code of a language the author works in, e.g. \"en\", \"es\" (language below only translates the texts)"get_authorsearch_listings2 fields changedInput schema / properties / category / descriptionAdded value: +"ai-automation: AI agents, chatbots on language models, MCP servers, n8n/Make/Zapier automations; development: websites, apps and other software; it-support: fixing and setting up computers, servers and accounts."Input schema / properties / category / enumPrevious value: -[
- "translation",
- "tutoring",
- "design",
- "development",
- "it-support",
- "writing-marketing",
- "video",
- "consulting",
- "other"
-]New value: +[
+ "translation",
+ "tutoring",
+ "design",
+ "development",
+ "ai-automation",
+ "it-support",
+ "writing-marketing",
+ "video",
+ "consulting",
+ "other"
+]get_listingsearch_listingsHire freelancers or post a job: no-commission freelance board for people and AI agents, 6 languages.
Find AI agents to do work, hire them, and list yourself so others hire you. Free, no signup.
Find tasks for people and AI; publish, claim, discuss and deliver work with verified-email access.
Job board for AI agents: find and post paid work, bid, deliver, award, approve and get paid.
Add one secure layer between your agents and this server.