ads_mastodon_interest_search

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

With no annotations, the description carries the full load: it usefully discloses that it writes bounded public evidence into a local research base (a real side effect) and that it never follows or contacts anyone. It omits permissions/auth needs, rate or per-hashtag limit behavior, and what the scoring output looks like, so disclosure is partial.

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?

Two tight sentences, front-loaded with the action and the safety constraint. Some jargon ('expanded interest discovery pack') costs a little clarity but 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 six-parameter, no-output-schema, no-annotation research-run tool, the description says nothing about what is returned (candidates, scores, hashtag breakdown) or how it relates to the interest research post/tag listing tools. An agent would have to experiment to know what calling it produces.

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 only 33%, so four of six parameters (account_id, project_id, min_signal_score, per_hashtag_limit) are undocumented in both schema and description. The text only implicitly touches min_signal_score ('score pain/intent signals') and save_to_research ('save ... evidence'), leaving the bounding and identity parameters unexplained.

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 gives a specific verb ('Run ... discovery pack') and resource (Mastodon interest discovery), and adds that it scores pain/intent signals and persists evidence to the local research base. That is concrete enough to separate it from plain reads like ads_mastodon_hashtag_search, though it never names the sibling it is closest to.

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 statement of when to choose this over ads_mastodon_hashtag_search or the ads_interest_research_* listing tools. The only guidance is a negative boundary ('never follows or contacts anyone'), which constrains conduct but does not route the agent between alternatives.

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