instagram_search_gate

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

Annotations already cover read-only, non-destructive, idempotent behavior. The description adds useful context such as the two-pass visibility stages, the under-18 floor being independent, and that every drop is counted by reason. No contradiction with annotations, and it provides meaningful behavioral nuance beyond the structured hints.

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 moderately long but every sentence carries meaning, explaining workflow, safety, and return values. It front-loads the purpose and usage, then lists args and returns clearly. It could be slightly trimmed, but the structure is logical and not wasteful.

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?

Given the tool's complexity (7 parameters, output schema, two-stage visibility), the description covers the workflow stages, return values (kept, dropped, reasons, next_step), and the safety invariant. It explains the 'costs nothing' aspect and the reason counting for tunability. Nothing essential is missing for correct invocation.

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 descriptions already cover all parameters (100% coverage), so baseline is 3. The description adds value by explaining which filters are effective at which stage (e.g., follower_min/max only work on the second pass because follower counts aren't visible in the first). This contextual insight helps the agent understand parameter behavior beyond the raw schema.

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?

Clearly states it filters the candidate pool using already-fetched data, naming the verb 'cut the pool down' and the resource (search results). It explicitly distinguishes from search tools by emphasizing no new data is fetched, and the phrase 'Run it straight after recall' positions it within the workflow.

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 explicit when-to-use instructions: 'Run it straight after recall, and again after enrichment' and explains that the first pass only sees privacy and handles while the second sees follower counts and bios. Also clarifies when not to rely on it for the under-18 floor and that over-removal can be loosened, providing actionable guidance.

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