ps_filter_items

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

With no annotations, the description carries the full burden yet only implies a mutation ('into the filtered stage') without stating whether items are moved, copied, or overwritten, whether the operation is idempotent, or what permissions/run state it needs. No side effects or reversibility are disclosed.

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 short sentence is front-loaded and free of padding, which is good. But at this length it is under-specified rather than concise, leaving no room for the behavioral or parameter context a 6-parameter tool needs.

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 pipeline-stage tool with 6 parameters, no annotations, and 0% schema documentation, the description is far too thin. The presence of an output schema excuses it from explaining return values, but nothing about inputs, ordering, or side effects is covered.

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 6 parameters, so the description must compensate and largely fails. The words 'scored' and 'filter' faintly gesture at the source_stage and threshold concepts, but config_path, topic_dedup, and periscope_path are entirely undocumented in both schema and description.

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?

It states a specific verb (filter) and resource (items) and names a target stage, so the general action is inferable. However, 'filtered stage' is pipeline jargon with no explanation of what filtering criteria apply, and it does not distinguish itself from pipeline siblings like ps_score_items or ps_enrich_items beyond the stage label.

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?

There is no guidance on when this stage should run relative to siblings (e.g., after ps_score_items, before ps_enrich_items), no prerequisites, and no mention of alternatives. The default source_stage='scored' hints at ordering but the description never states it.

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