Inspect model

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context beyond that: include_edges produces a large result on big models (a cost/size warning), and the tool returns aggregate counts of cells, memory, edit events and commits. It does not discuss latency or pagination, which keeps it short of a 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-loaded with the return contents, then usage, then exclusions, then the parameter caveat — a sensible ordering with no filler sentences. The opening enumeration is dense but each item is factual and useful; it is slightly long for what a routing decision needs.

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, so the description carries the full burden of describing return values, and it does so by enumerating every section of the summary. Combined with the alternative-tool routing and the cost warning for include_edges, an agent has everything needed to call this correctly.

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 earns more by explaining the consequence of include_edges ("adds every formula dependency edge, which is large on big models") and pointing to trace_dependencies as the narrower alternative for a single-cell chain. session_id semantics are left entirely to the schema, which is acceptable given its documented provenance.

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 opens with a specific verb and resource ("Summarize a session's structure") and then enumerates exactly what is returned: sheet indexes, names, used rows/columns, defined names and targets, iterative-calc settings, and four counts. That specificity lets an agent distinguish it from siblings like audit_workbook or trace_dependencies without opening any schema.

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 states the primary use case ("find your way around a workbook before reading or editing it") and then names concrete downstream consumers of the output (rename_sheet, delete_sheet, define_variable for sheet indexes; get_outputs and set_inputs for names). It also gives explicit exclusions with alternatives: use trace_dependencies to follow a chain from one cell, and audit_workbook for errors, plugs and broken references.

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