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

Annotations already establish read-only, non-destructive, open-world behavior, so the safety profile is covered. The description adds substantial context beyond that: the 30-day window, exclusion of prior boosts, the 48-hour visit/signup prediction model, engagement-vs-usual comparison, and the 'under 500 views = untested, not weak' interpretation. Return shape is only loosely implied (the 'boosted' list), keeping it short of 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?

Dense but front-loaded: it leads with what the resource is, then ranking logic, then a caveat, then routing, then cost. Each clause carries information, though the parentheses and semicolons make it slightly tangled to parse.

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?

With no output schema, the description carries the return-value burden and mostly does: ranked posts, prediction signals, an 'untested' marker, and a separate 'boosted' list. It stops short of describing volume, pagination, or exact fields, but for a single-input read tool it is adequate.

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?

Only one parameter and the schema documents it at 100% coverage ('Their X handle, when the audit did not store one'), so the baseline is 3. The description adds nothing about the handle — reasonable, since the schema already states its emergency/fallback role.

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?

Names the specific resource (the founder's original X posts from the last 30 days), the filtering rule (minus previously boosted), and the ranking criteria. It clearly distinguishes itself from boost_plan by routing the latter to a different case, though the verb is implicit rather than stated outright ('returns posts worth boosting').

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?

Explicit gate: 'Only when the founder asks which post to boost,' with a clear alternative path — 'a post they name goes straight to boost_plan.' It also flags the tool as 'Free,' so an agent knows the cost trade-off. Nothing 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.