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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses behaviour the agent could not otherwise know: the report is recomputed from its definition each time so it stays current rather than snapshotting data, saving is all-or-nothing ('Every block must run, or nothing is saved'), and an existing report's title/description/blocks are overwritten on update. It also states the return value (the report's address when the company has Reports pages).

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?

Every sentence carries distinct information (currency model, workflow, replace semantics, atomicity, return value), but the opening clause is a comma-spliced run-on ('where it is worked out again from the copy each time, so it stays current, and run_report runs it') that would read better as separate statements. Size is appropriate for the tool's complexity.

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 deeply nested save tool with no output schema, the description covers what an agent actually needs: the required preview step, the update-vs-create switch, atomic failure behaviour, and the fact that a URL is returned. Nothing material for correct invocation 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?

The nested schema is already heavily self-documented, but the description adds meaning on top: the report payload is identical to preview_report's, and report_id is a replace-not-append switch that overwrites title, description and blocks. It leaves recent-connection/auth or payload-size concerns unstated, but the parameter semantics themselves are clarified.

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 and resource ('Save a report') and immediately disambiguates it against siblings: preview_report builds the same payload, run_report executes the saved version, list_reports names existing ones. An agent can place this tool in the report workflow without opening the 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?

Gives an explicit precondition ('preview it and show the user first') and the create-vs-update rule ('report_id replaces that report's title, description and blocks. Omit to make a new one'). It also names the alternative that consumes the result (run_report), so the when-to-use decision is fully determined.

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