aeo_filter_prompts

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so safety is covered; the description adds real value beyond that with hard limits (175 items per call, 300 characters each), accepted input shapes, and the return structure {kept, removed, summary}. It does not say what happens when the limits are exceeded (error vs. truncation), which keeps it from a 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?

Three compact sentences, front-loaded with the action and the removal taxonomy, then input constraints, then return shape. The parenthetical list is dense but every item is functional information; there is 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 read-only filtering tool the description covers input format, per-call limits, and return shape, which is substantial given no output schema exists. The notable gap is the three optional behavioral parameters (brand, geo_target, competitor_domains), whose effect on filtering is entirely undocumented.

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% across 4 parameters, so the description carries the full burden. It explains 'items' well (both accepted formats and size limits) but says nothing about 'brand', 'geo_target', or 'competitor_domains', even though these clearly drive which entries are classified as brand-variants, geo noise, or other-brand noise.

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 ('Clean') and resource ('imported keyword/prompt list') and enumerates exactly what counts as noise (operators, year-stamps, foreign, geo, brand-variants, other-brands, dupes). This makes it clearly distinguishable from siblings such as aeo_audit_prompts, aeo_cluster_prompts, and aeo_generate_prompts, which operate on prompts but do not clean imported lists.

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 phrase 'imported keyword/prompt list' implies the use case (pre-processing raw imports) but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent can infer the context but must decide on its own whether to run this before or instead of the audit/cluster siblings.

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