scratchpad_read

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

With no annotations provided, the description adds useful behavioral context: notes are from the current session, returned newest first, and expired/old notes are automatically purged ('Expired notes are automatically cleaned up'). This goes beyond the schema, though it doesn't mention read-only safety explicitly (but that's implied by 'read').

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?

Two sentences, front-loaded purpose, every clause adds value: what it does, ordering, when to use, and note retention behavior. No fluff.

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?

For a simple read operation with only two optional parameters, this is nearly complete. It covers purpose, usage timing, and the auto-purge behavior. Lacks explicit return type description, but without an output schema and given the simplicity, it's adequate. Could benefit from noting it returns only unexpired notes (implied by purge).

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 covers 100% of parameters with descriptions including defaults. The description adds no additional parameter context beyond the schema, so baseline 3 is appropriate.

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 clearly states the tool reads short-term working notes from the current session's scratchpad, with a distinctive 'newest first' ordering. It uses a specific verb+resource construction and is distinguishable from sibling tools like scratchpad_write and scratchpad_clear.

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?

Explicitly states when to use it ('when resuming a task to recover in-flight state'), providing clear context. It doesn't explicitly say when NOT to use it (e.g., vs memory tools), but the 'short-term' qualifier implies a distinction from long-term memory.

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