Avito Shopping MCP

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real context beyond them: the session is local and protected, and live=true triggers an actual outbound request through the saved session, which matters for an open-world 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?

Two tight sentences with the core check front-loaded and the optional flag second. 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 one-optional-parameter diagnostic tool with strong annotations and no output schema, the description covers what it verifies and the side effect of live mode. It could say more about what the check reports (session present/expired), but nothing essential 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 0% and the single property has no description, so the description must carry the meaning. It does explain that live=true sends one request through the saved session, while the default false is left implicit but reasonably inferable from 'also'.

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 ('Check whether a protected local browser session exists') and the optional live probe. This clearly separates it from avito_setup_session, which establishes rather than verifies the session.

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?

Explains the conditional use of live=true ('also send one lightweight request'), which is genuine usage guidance. However, it never says when to prefer this over avito_setup_session or what to do if the check fails, so the routing guidance is only implied.

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 the useful fact that a seller profile is bundled in, but it discloses nothing about auth/session requirements, behavior when the listing id is invalid or removed, or rate limits.

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

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

One front-loaded sentence that opens with the verb and resource. The long field enumeration is slightly list-heavy but justified since no output schema exists to convey the return shape.

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 no output schema, describing the returned fields is exactly the right compensation. It stops short of covering error/not-found behavior and the session prerequisite implied by the sibling avito_setup_session.

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 'item' parameter already documents both the URL form and numeric id, so the description adds nothing beyond the schema. Baseline 3 is appropriate when the schema fully carries parameter meaning.

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

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

States a specific verb ('Get') and resource ('one Avito listing') and enumerates the returned fields, making the single-item lookup role clear. It implies contrast with avito_search but never names or explicitly differentiates from that sibling.

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?

'Get one' hints that this is single-item retrieval versus a search, but the description never states when to use it over avito_search or avito_seller_reviews, nor any prerequisites such as needing an authenticated session from avito_setup_session.

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, openWorldHint, idempotentHint, and non-destructive behavior. The description adds meaningful context by enumerating returned fields and noting seller name and rating are included only 'when Avito shows them', which is valuable since there is no output schema. It still omits auth/session needs and rate limits.

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 no filler; the purpose is front-loaded and the return list is compact. Every sentence contributes to selecting or interpreting the tool.

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, and the description usefully explains the return fields and their conditional presence. With full schema coverage and annotations covering safety, the definition is nearly complete, though it omits any reference to setup prerequisites or alternative tools.

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

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

Schema description coverage is 100%, so all seven parameters are already documented in the schema. The description only echoes the city scope via 'in one city' and adds no format, default, or syntax details beyond what the schema provides.

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

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

States a specific verb and resource ('Search Avito classifieds'), scopes it to 'one city', and names the return entity (listing). It is readily distinguishable from siblings like avito_item (single listing) and avito_seller_reviews (reviews).

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 gives no when-to-use or when-not guidance. It does not mention alternatives such as avito_item for retrieving a single listing, nor does it note whether avito_setup_session is a prerequisite. The only implicit condition is the city scope.

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 behavior is covered. The description adds genuine context that the reviews span all seller deals rather than the given listing, but it says nothing about session/auth requirements or how many reviews are retrievable by default.

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 no filler; the core action and payload are front-loaded, and the scoping caveat follows immediately. Nothing needs trimming.

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 names the return contents (reviews, overall rating, score distribution) and the cross-listing scope. It stops short of covering failure modes (invalid/expired listing, seller with no reviews) or session prerequisites that a sibling tool manages.

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% — both 'item' (URL or numeric id) and 'limit' (newest first, max 50) are fully documented in the schema. The description's 'newest reviews' phrasing only restates the schema's ordering, adding no new parameter meaning. 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 (read) and resource (the seller's newest reviews) plus the returned payload (overall rating and score distribution). It also draws a clear boundary against the listing-scoped siblings: reviews cover all of the seller's deals, not only this listing.

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 scope statement implies when this is useful (assessing seller reputation), but no alternatives are named — nothing says whether to prefer avito_item or avito_search, and there are no prerequisites such as needing an active session via avito_setup_session. Usage is inferable but not 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 declare non-readOnly, openWorld, non-idempotent, non-destructive, so the safety profile is already covered; the description adds substantive behavior beyond that: a temporary browser window is opened, results must be served before proceeding, the user may have to pass an access check (a human-in-the-loop dependency), the session is persisted locally, and the window is closed. It stops short of saying where the session is stored or how long it remains valid.

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 that proceeds in execution order (open, wait, save, close) with no filler, and it front-loads the browser-window action. It is efficient, though cramming four steps plus the access-check caveat into one sentence slightly reduces scanability.

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 convey the outcome — it does (session saved locally, window closed) — and annotations cover the side-effect profile. However, for a stateful setup tool that other sibling tools presumably depend on, it omits the undocumented timeout parameter, session persistence location/expiry, and any ordering relationship with avito_search/avito_item, leaving a moderately sized gap.

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

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

Schema description coverage is 0% for the single parameter timeoutSeconds, so the description carries the full burden — yet it never mentions the timeout, its default of 120s, its 30–300s range, or what happens when it elapses. The phrase 'wait until Avito serves search results' gestures at a bounded wait but adds no actionable parameter meaning.

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+resource — it sets up (opens, waits, saves, closes) a local Avito session — and enumerates the concrete steps. It does not reference any sibling by name, but since no sibling competes for this setup role, an agent can still tell it apart from avito_search/avito_item. Clear but without explicit sibling differentiation.

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 never states when to call this tool: not whether it must run before avito_search/avito_item, not what triggers a re-run, and not what happens if a session already exists. Usage is only inferable from the tool name and the phrase 'save the session locally'. No when/when-not guidance is provided.

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