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

Annotations already establish readOnly, idempotent, closed-world behavior, so the description adds real value beyond them: the measurement window (day after marked done through yesterday, max 92 days), the equal-length prior comparison period, the enumerated row states, and the key limitation that it 'never says what caused a difference'. The one gap is that it does not describe ordering or result volume for large reviews.

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?

The purpose is front-loaded, and the closing sentences ('It compares two periods and never says what caused a difference. Open and dismissed recommendations have no row.') earn their place. But the opening is a single sprawling construction with nested parentheses, template placeholders, and jargon that make it hard to parse on first read.

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 carries the burden of explaining return values, and it does: one row per qualifying recommendation, with a state, a plain sentence, the window, and the numbers now and before. Scope and exclusions are defined; only ordering and behavior at the 92-day cap for older recommendations are left implicit.

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%, with both project and review_id fully documented in the schema, so the baseline is 3. The description only says 'For a saved review' and adds no format, sourcing, or fallback detail for the two parameters beyond what the schema already provides.

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 states a specific retrieval: for a saved review, it returns one follow-up row for every recommendation whose status is 'done', re-reading the numbers named in its watch text over a defined comparison window. It is specific about the verb and resource, but the heavy jargon ('watch text', '{{eN.field}}', 'watch_evidence's main number') and lack of explicit differentiation from siblings like get_review_data keep it from a 5.

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?

Usage is implied by 'For a saved review' and by the exclusion 'Open and dismissed recommendations have no row', which tells the agent which recommendations qualify. However, there is no explicit when-to-use guidance versus get_review, get_review_data, or update_review_recommendation, and no prerequisites beyond the schema's project/review_id.

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