MCP do Afiliado

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

Goes well past the annotations: it discloses that stored panel credentials are used, that malformed input (missing https://, trailing punctuation) is auto-corrected, and critically that conversion is partial-success — invalid entries land in "invalid_urls" while the rest of the batch still converts. It also states the response shape and which field is meant for publishing.

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-loads purpose, then the mandatory-input rule, then edge-case handling, then the return contract — a logical order for an agent to act on. Every sentence carries distinct information; nothing is repeated from the schema 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 two-parameter conversion tool with an output schema and annotations already covering the safety profile, the description supplies everything else: credential source, normalization behavior, partial-failure semantics, and batching guidance. No gap remains that would cause an incorrect call.

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%, which already sets a baseline of 3, but the description adds real meaning: the schema marks zero required parameters while the description declares one of "url"/"urls" is mandatory, and it explains batching limits and the corrected-then-returned behavior. This closes a gap the schema leaves open.

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 ("Converte ... links ... em links de afiliado") plus the scope (conta do usuário, credenciais do painel). This is clearly distinct from the read-only siblings get_bot_info, get_product and search_products, so an agent can pick it 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 explicit mode selection between "url" (single) and "urls" (batch), including the 150-item ceiling and the instruction to split into batches beyond that. It does not name any alternative or exclusion relative to the sibling tools, so usage context is clear but not fully comparative.

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 this as read-only, non-destructive, and closed-world, so the safety profile is covered. The description adds useful behavioral context about the returned capability data, including provider grouping and sample domains, though it does not discuss rate limits or output shape in detail.

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 front-loaded with the core purpose, followed by concrete usage conditions and a specific alternative. Every sentence contributes useful routing or capability information without unnecessary repetition.

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 parameterless read-only capability-inspection tool, the description covers what it returns and when to call it. Since an output schema exists, it does not need to enumerate return fields, and the remaining guidance is sufficient for 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?

The tool has zero parameters, so there is no parameter meaning to explain beyond the schema. The description correctly does not invent parameter details; baseline 4 applies for a parameterless tool.

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

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

The description states a specific verb and resource: it shows what the account supports, including active-search marketplaces, public catalogs with monetization flags, and convertible routes grouped by provider. It also names related tools (search_products, convert_links) so an agent can distinguish this capability-inspection tool from actual search or conversion tools.

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 explicit triggers: use when a search or conversion fails because a site is not configured, or when the user asks what the bot can do. It also routes the agent to convert_links for checking whether a specific domain converts, which is a clear alternative for a related need.

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?

Beyond readOnly/openWorld annotations, the description discloses substantial behavior: per-source data provenance (Shopee Open API, AliExpress Affiliate API, public Kabum/Magalu catalog, public product page elsewhere), the degraded fallback when no credential is set (affiliate_url and final_url null, monetized:false), Amazon's credential preconditions, and where price history comes from. The harbor is that it doesn't state error behavior for unsupported URLs, but the behavioral context is otherwise rich.

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 paragraph, and the operative constraint (URL-based lookup) is front-loaded, but a large share of the text enumerates return fields that the output schema already defines. The semicolon-clause listing of optional fields per store makes it heavier than it needs to be.

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 read-only detail tool with an output schema and only one required parameter, the description covers source-specific behavior, credential preconditions, and degraded modes, which is close to complete. It omits what happens with an unsupported or invalid product URL, which is the one remaining gap an agent would want.

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 both parameters (url and history_limit) are already documented in the schema; baseline 3 applies. The description only alludes to the price-history field's existence implicitly through the returned data list and adds no format or usage meaning beyond 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?

The description names a specific verb and resource ('Dados de um produto a partir da URL') and enumerates the returned fields, so an agent can tell this is a single-product detail lookup. It does not explicitly contrast with sibling tools like search_products or convert_links, so it falls short of the 5 bar for 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?

Usage is implied by the URL-based input and the per-store notes, and useful context is given (Kabum/Magalu work without credentials; Amazon requires a Credential ID/Secret). However, it never states when to use this instead of search_products, nor what happens for unsupported URLs, so the when-to-use guidance remains implicit.

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/openWorld/non-destructive, and the description adds genuinely new behavior: pagination semantics (count equal to limit usually means another page exists, but with active filters a smaller count does not guarantee the end), partial-failure reporting via "sites_failed", and the caveat that a failed site does not mean the product is absent there. It stops short of auth/rate-limit details, so a 4 rather than 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?

Purpose and marketplace scope come first, then filtering/sorting, then pagination and failure caveats — a sensible information hierarchy. Despite the density of parentheticals every sentence contributes operational detail an agent would otherwise have to infer.

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 11-parameter, multi-marketplace tool with nested site_filters, the description covers the hard parts: default site behavior, opt-in sites, pagination interpretation, and partial failure. Return fields (image_url, price, count, page) are described even though an output schema exists, which is mildly redundant but not harmful.

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 schema already explains every parameter including the site_filters marketplace-specific shapes. The description largely restates schema content (price_min/price_max range, sort: price_asc = cheapest) with only marginal added meaning around currency units. Baseline 3 applies when the schema carries the load.

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 ("Busca produtos por palavra-chave") plus the exact scope: which marketplaces are queried by default and under which API credentials (Shopee/AliExpress/Amazon via Creators API, Kabum/Magalu only when "site" is set). An agent can distinguish this from get_product (single item) and convert_links (link conversion) without opening any 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 concrete usage context: filter by price range, sort with price_asc for cheapest first, and the explicit rule that kabum/magalu are opt-in only. It even prescribes when to reach for key_seller_only (when many unavailable sellers appear). What it lacks is an explicit statement of when NOT to use this tool in favor of get_product or get_bot_info, which keeps it below a 5.

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