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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond that: return format ('structured fields the model can render'), a permission prerequisite, and the output scope (changes, risks, blockers, next steps).

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?

Two tight sentences: the first states purpose and content scope, the second covers return format and permission needs. Front-loaded, no redundancy, and every sentence earns its place.

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 simple two-parameter read-only tool with no output schema, the description covers purpose, output content, default behavior, and permission requirements adequately. The main gap is routing guidance versus similar status/portfolio tools.

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 50%: sinceDays is already documented as 'Default 7, max 90.' The description restates its effect ('what changed since sinceDays ago'), adding marginal clarity, but says nothing about projectId (format, source, or why required). At 50% coverage it only partially compensates.

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?

Specific verb+resource ('Generate an executive status summary for one project') with enumerated covered content (changes, risks, blockers, next steps). Scope is clear, but it does not name or distinguish itself from similar siblings like generate_status_report or compose_status_digest.

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?

No when-to-use, when-not, or alternative routing is provided. 'Caller must have visibility into the project' is a permission prerequisite, not usage guidance, leaving the agent to infer when this tool should be chosen over portfolio_summary or generate_status_report.

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