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

Useful disclosures beyond annotations: it is read-only in effect, costs nothing, and requires the write scope (a non-obvious auth requirement worth stating for a read tool). But "Free: nothing is charged" directly conflicts with the schema's budgetUsd parameter (default 2, max 10), so an agent cannot tell whether this call can spend money — a misleading behavioral claim on the one dimension that matters most here.

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?

Three short sentences, front-loaded with what the tool does, with no filler. Slightly loose ordering puts the cost/auth notes after the content list rather than up front, where they would prevent a budget misread.

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 enumerating return contents is bonus rather than necessity, and the auth requirement is a good addition. However, the unaddressed budgetUsd/cost ambiguity leaves a real gap for a tool that accepts a spend cap.

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 the schema already documents ids and budgetUsd fully; the description only echoes the 1-3 count that maxItems/minItems encode. It says nothing about budgetUsd, which is precisely the parameter most in tension with its "Free" claim.

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 (exemplars from reference_search) and enumerates what comes back: why they worked, structure and beats, transcript and on-screen text, rebuild recipe. This is clearly distinguishable from the sibling reference_search, which locates exemplars rather than reading them in full.

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?

"Read 1 to 3 exemplars from reference_search" makes the prerequisite call explicit and implies this is a second step after search. It gives no when-not-to-use guidance or alternatives (e.g. references_browse, references_list), so it falls short of full routing.

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