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

Annotations already declare a non-read-only, non-destructive, non-idempotent, open-world write. The description adds genuinely new behavior: the text is sent to a model provider, everything is staged as PENDING, and nothing becomes fact until the user approves it in the Stash inbox. That pending-review model is important context, but it still omits the cost and latency of the model classification and what the response returns.

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?

Four sentences with the core action front-loaded, followed by data flow, then the review guarantee, and finally the URL edge case. Every sentence carries information, though the split between the description and the text parameter's own description repeats the 'stated or confirmed by the user' constraint.

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 two-parameter tool with no output schema and full schema coverage, the description covers purpose, data flow and the pending-review outcome, so an agent can call it correctly. It could still state what the response looks like and whether repeated calls create duplicate pending items.

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 coverage is 100%, so the schema already documents both parameters, including transcript_source selecting the transcript classifier. The description reinforces that text must be user-stated business facts and adds the URL-edge rule, but it adds little syntax or format guidance beyond the schema, so this scores at the documented baseline.

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?

States a specific verb and resource: stages business facts the user stated or confirmed into the FeedSquad Stash, as a freeform note or call transcript, covering business, audience, positioning, voice and strategy. That is far more specific than the title. It does not, however, distinguish itself from the sibling propose_stash_items, which an agent would need to choose between.

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?

Gives clear inclusion criteria (only facts stated or confirmed by the user in the current conversation) and an explicit exclusion (text that is only a URL stages nothing, because a URL alone does not identify the company). It stops short of naming an alternative tool or saying when to prefer propose_stash_items, so the routing between the two sibling staging tools is left to inference.

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