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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds 'read-only' explicitly, which aligns. It also mentions bulk support and lists filters. It does not describe return format or pagination beyond 'cursor', but given the annotations cover safety, the description adds meaningful context about the action space. No contradiction with 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?

The description is relatively compact for a tool with 15 parameters and multiple actions. It is front-loaded with the read-only intent and action list. The main issue is it lists multiple actions that are not all relevant to this specific tool, which adds noise. However, the 'Flattened action: search' clarifies the primary purpose. Slightly verbose but generally efficient.

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?

Given the tool's complexity (15 params, no output schema, no schema descriptions), the description is incomplete. It provides a filter list and bulk support, but does not explain expected parameter formats (e.g., date range 'started_at_ini/end' without specifying ISO format), pagination behavior, or what the response contains. The output schema is absent, so the description should cover more, but it does not. It is adequate for simple search but not complete for a complex search 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?

The schema has 15 parameters with 0% description coverage (no descriptions in schema). The description lists the filters in parentheses: 'subscription_status, product_id, contact_email/contact_doc/contact_name, started_at_ini/end, last_status_at_ini/end, cursor'. This provides some meaning, but it does not explain the format or expected values for any parameter. With 15 parameters and zero schema descriptions, the description should do more to clarify semantics, but it only names them. The bulk support note clarifies 'ids' and 'product_ids', but that's minimal. Baseline is lower because description coverage is 0%.

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 this is a read-only tool for 'Assinaturas no Guru (leitura)' and lists the 'search' action with relevant filters. It clearly distinguishes from sibling write tools like guru_subscriptions_write_cancel. However, it conflates multiple actions (search, get, activities, etc.) into one description, and the focused action is 'search' as indicated by '[Flattened action: search]'. The purpose is clear for the search action but slightly muddied by listing all other actions.

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 searching subscriptions with various filters and mentions 'Bulk support: accepts ids, product_ids for batched execution.' This gives context on when to use bulk. However, it does not explicitly state when not to use this tool or what alternatives exist for other actions (e.g., guru_subscriptions_get for individual get). The sibling list shows many other tools that may be alternatives, but no guidance is provided.

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