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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial extra context: workspace scoping, independence of tables from versions, the fact that reader-appended rows are omitted from `rows`, and the revision-fetch prerequisite for writes. These are behaviors the annotations cannot convey.

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 purpose and mode-switching behavior, and dense with useful detail rather than filler. It is quite packed into one paragraph, but nearly every clause carries information; little could be cut without losing routing or behavioral guidance.

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?

With no output schema, the description explicitly enumerates return contents for both modes (name, revision, columns, row count, size, write-back switch, limits; and columns/rows/revision with csv). Combined with scoping and prerequisite notes, an agent has everything needed to call it 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?

Adds real meaning beyond the schema: `table` omitted lists every table, present returns the full table, and `format=csv` 'adds CSV text' rather than replacing JSON. `proposal_id` is undocumented in both schema and description, a minor gap, but the two behavior-defining params are well covered.

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 ('Read data tables attached to a page') and immediately distinguishes itself from siblings by naming set_data (must precede it) and list_data_rows (for reader-appended rows). An agent can tell it apart from other read tools 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?

Explicitly routes usage: omit `table` to list all tables, pass `table` to read one full table, and 'always call this before set_data to obtain the current revision'. It also names the alternative for reader-appended rows (list_data_rows) and clarifies that viewer-page reads do not go through this tool.

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