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 a genuinely useful non-obvious trait: it does not recompute current data, pointing the agent to run_insight_query for fresh numbers. It stops short of describing pagination or empty-list behavior, so not a full 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?

Three tight sentences, each earning its place: what it returns, the staleness caveat with an escape hatch, and the usage trigger. Front-loaded with the core purpose.

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?

No output schema exists, so the description usefully enumerates the returned fields. Combined with the annotations and a fully documented param, 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 description coverage is 100% and the single optional id parameter is fully documented in the schema, so the baseline is 3. The description adds return-field context but no additional meaning about how id behaves.

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 ('List the user's pinned dashboard insights') and even enumerates the returned fields (id, title, viz spec, sort order). It clearly distinguishes itself from propose_saved_insight and run_insight_query, both named in the text.

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 tells the agent when to use it: 'to see what's already pinned before proposing a new one, or to find an insight's id/spec to edit or rerun.' It also routes the fresh-data case to run_insight_query, giving a named alternative with its selection condition.

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