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

Annotations declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds genuinely new context: successful deliveries are saved privately to the account, consume shared research credits, and unavailable receipts fall back to full delivery. Credit consumption and persistence are the kind of side-effect disclosure annotations do not provide.

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 main action is front-loaded, but the prose is dense and abstract – 'Selected posts, context, reused wording and delivery coverage remain distinct' is opaque and does not obviously help an agent decide anything. Several sentences restate schema concepts rather than earning their place.

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 values need not be explained, and the description covers side effects and reuse/fallback behavior. For a 9-parameter, deeply nested tool it still leaves usage routing and the many selector kinds entirely to the schema, and it never clarifies the fresh-vs-captured operating model.

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?

With schema coverage at 33% but richly described nested objects (selector, reading, basis all carry inline explanations), the schema already does much of the work. The description maps 'fresh or retained' onto the basis modes and gestures at delivery/reuse semantics, but adds little concrete parameter meaning beyond what the schema documents.

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 names a specific verb (Read) and concrete resources (stored post versions, recorded counters, source citations, reply/quote/repost context). It is clear about what the tool returns, but it never distinguishes itself from siblings like discover_evidence or measure_evidence, so the agent must infer the boundary.

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 explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The phrase 'explicit fresh or retained selection' hints at two bases but does not tell the agent when each applies or how this tool relates to discover_evidence/measure_evidence.

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