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

Annotations already cover safety (readOnlyHint) and reach (openWorldHint), so the bar is lower. The description adds real behavioral context: one event per change with its own time and precision, a recorded 'when HEY first knew' timestamp, attached evidence, newest-first default ordering, and retraction semantics ('HEY no longer makes that claim').

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-loads the resource definition, then usage triggers, then pagination mechanics. Dense but mostly earns its space; the closing aphorism 'Facts, never causes' is stylistic rather than operational and is the one expendable fragment.

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 10-parameter read tool with no output schema, the description covers purpose, filtering intent, ordering, pagination/cursor persistence, and even the shape of returned events (time, precision, first-known, evidence). It leaves the remaining filter parameters (domain, type, project, since/until) and the response envelope largely to the schema.

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 70%, so the baseline is 3, and 10 parameters include several undocumented in the schema (until, domain, type, project). The description compensates for the hardest ones by explaining the cursor/sync model for after and before and explaining that facts are timestamped by their own time — meaning beyond the schema's terse 'Sync forward from this cursor'.

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 ('canonical change ledger: what changed on Robinhood Chain or one project') with an enumerated scope (releases, ships, status moves, deployments, verification, unlocks). It is distinguishable from siblings like project_diff, get_project_timeline, and get_evidence by framing itself as the per-event ledger rather than a comparison or rollup.

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 names trigger utterances ('what changed', 'what happened since', 'anything new on X') and gives concrete how-to-use guidance for pagination (browse newest first; pass after=c1.0 or a kept cursor; keep the cursor each answer gives). It lacks any when-not-to-use or named alternative for overlapping cases.

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