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

Annotations already declare readOnly/non-destructive/closed-world, and the description adds context beyond them: the cost model (budgetUsd default 2, max 10, held and released, hence free) and the auth requirement ('needs the write scope'). The write-scope note is slightly at odds with the read framing and could confuse, but the added cost/auth behavior is genuine value.

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 dense single paragraph that front-loads purpose, then enumerates returned content, then cost and scope. Every clause carries information, though the budget sentence partially duplicates the schema.

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?

An output schema exists, so return structure needn't be explained; the description instead covers what conceptually comes back, the workflow linkage, cost behavior, and auth scope. Coverage is solid, with only the write-scope/read-only tension left ambiguous for an agent.

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 100%, so both parameters (ids, budgetUsd) are already fully documented in the schema. The description only restates the same facts (budget default/max, ids count), adding no syntax or meaning beyond the schema. Baseline 3 applies.

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 (read) and resource (1-3 exemplars from reference_search) plus exactly what the read yields: why they worked, structure/beats, transcript, on-screen text, and a rebuild recipe. It is clearly distinguishable from the sibling reference_search (search vs. full fetch).

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?

It names the source flow explicitly ('from reference_search') and how many to pass (1-3), so an agent knows this follows a search and consumes its ids. It stops short of stating when NOT to use it or naming edge alternatives, so it is context-rich but not exclusion-complete.

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