add-filters

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

The description only states what the tool does and does not disclose side effects, required permissions, rate limits, or response behavior. The annotations indicate readOnlyHint: false (write operation), but the description adds no extra behavioral context. For a write operation, an agent would benefit from knowing what the response contains or any side effects, which are not mentioned.

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 a single, concise sentence that conveys the essential purpose without any fluff or redundant information. It is well-structured and immediately understandable.

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?

The description provides enough context for an agent to know that this tool creates personal filters using query syntax. It implies that filters are custom views. However, it does not mention any prerequisites, limits (e.g., maximum number of filters), or what the response looks like. But for a simple add operation, the given information is largely sufficient. The presence of a full output schema (not shown) may fill some gaps, but the description alone is mostly complete.

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 input schema provides comprehensive descriptions for all parameters (name, color, query, isFavorite, description) with examples and valid values. The tool description itself adds no additional meaning about parameters. Since the schema already covers semantics fully, the description does not need to repeat them, but it also does not enrich them further. This is an adequate but not outstanding score.

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 clearly states the tool's action: 'Add one or more new personal filters.' It specifies the resource (personal filters) and the verb (Add), making it obvious this is a creation operation. It also briefly explains what filters are, which helps an agent understand the domain.

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 is explicit about creating new filters (not updating existing ones) by using the word 'new.' While it doesn't directly mention alternative tools like 'update-filters' or 'find-filters,' the context from the sibling list and the clear 'Add' verb imply when to use this tool. The description could be slightly more explicit about not using it for modifications, but it is sufficiently clear for an agent to decide.

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