Get outputs

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

Annotations only declare readOnlyHint and openWorldHint; the description goes further by disclosing the 2,000-cell cap, that Excel errors return as type "error" rather than a tool failure, and that an unknown name/invalid ref fails the whole call. This is genuine beyond-annotation context. It stops short of describing ordering, partial-failure behavior for mixed valid/invalid keys, or pagination, so not a perfect 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?

Front-loads the purpose, then usage context, then return shape, then the alternative routing — a sensible order with no filler sentences. It is a dense single block, however, packing argument syntax, limits, error semantics and return shape into one run-on paragraph, which slightly hurts scanability.

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?

There is no output schema, and the description supplies the return shape ({values: {<name or ref>: {cell, type, value}}}), error-cell semantics, the size limit, and failure behavior for invalid keys. For a two-parameter read tool with annotations covering the safety profile, nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so the baseline is 3; the description adds real meaning beyond it — accepted forms (defined names, "B4", "Sheet1!B4", ranges), one entry per cell, the 2,000-cell limit, and the semantics of omitting names entirely. It does not clarify whether mixing names and ranges in one array has any constraint, but the added value is clear.

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+resource ("Read computed values from a session") and immediately scopes it as the way to check what formulas return. It explicitly distinguishes itself from get_formula_range (formula text) and trace_dependencies (what feeds a value), so an agent can route correctly without opening sibling schemas.

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?

Gives positive usage context ("after set_inputs", checking formula results) and explicit exclusions with named alternatives for both adjacent needs. The "omit names to read every defined name" clause also covers the default case, leaving little to inference.

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