suggest_filter

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

With no annotations provided, the description must carry the behavioral burden. It clearly states that the tool does not apply the filter but shows a banner, and that invalid DSL expressions are rejected. This discloses the non-mutating nature and error handling behavior, which is adequate for a suggestion tool. It does not mention every edge case, but the key behaviors are covered.

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 exceptionally concise, consisting of two short sentences that front-load the core distinction (proposal vs. application) and the rejection behavior. There is no redundant wording, and each sentence earns its place.

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 tool is simple with two parameters and an output schema present. The description captures the essential behavior (proposal, not application) and the DSL rejection rule. For an agent to invoke it correctly, nothing critical is missing. The reference to 'banner' provides sufficient detail about the delivery.

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?

Both parameters are fully described in the input schema (100% coverage). The description adds no extra meaning beyond what the schema already provides for reason and dsl_expr. Since the schema covers the semantics well, the baseline of 3 is appropriate; the description does not need to compensate.

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 explicitly states a specific action (propose a filter) and the target (the human). It contrasts with applying, clarifying that this is a suggestion mechanism, not a direct modification. This distinguishes it from sibling tools like get_active_filter or apply_style, even without naming them, and uses the specific verb 'propose'.

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 the use case: when the AI wants to recommend a filter it thinks the user should see, and the human decides whether to apply it. This provides clear context for invocation but does not explicitly name alternative tools or state when not to use it. The contrast with 'not applying' gives partial guidance, so it scores slightly above average but lacks explicit exclusions.

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