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

With no annotations, the description carries the full behavioral burden and does so: it discloses the idempotency identity tuple, the update-vs-append semantics ('latest value wins', metadata merge rules), and the purely additive many-to-many insight linkage with the removal path. These are non-obvious traits an agent could not infer from the name or schema.

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?

It is long, but it is front-loaded (purpose first, then idempotency, then linkage) and uses labeled sections (IDEMPOTENCY, INSIGHT LINKAGE) rather than prose sprawl. Some material on insight linkage duplicates what the schema's insightId/insightIds descriptions already say, which is the only real waste.

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 mutation tool with no annotations and no output schema, the description closes every gap an agent needs: what is written, what happens on re-write, how links accumulate and how to remove them, and where canonical keys come from. Nothing required to call it correctly 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?

Schema coverage is 100%, so baseline is 3, but the description adds real value beyond the schema: it tells the agent to pass canonical registry keys, how to discover them (call query_metric_snapshots with no args or read the error hint), how periodKind+periodLength combine so 'last 30 days' and 'April 2026' don't collide, and why sourceParams matters for reproducibility.

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+resource ('record one or more structured metric snapshots') plus the domain purpose (time-series analysis). It explicitly distinguishes itself from the sibling query_metric_snapshots and from update_insight, so an agent can route without opening any 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 trigger ('use this whenever you cite a metric in an insight, weekly digest, or benchmark'), names the alternative behavior it replaces (burying the number in prose), and points to the counter-tool for unlinking via update_insight(unlinkSnapshotIds). When-to-use and when-to-use-something-else are both covered.

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