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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the 16:30 ET (or 60-minute) gating on recap visibility, the fallback to the previous session's recap, the deliberate ignoring of date/time for unauthenticated calls, and caps on GEX nodes and changes. These are exactly the behavioral details an agent cannot get from structured fields.

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?

Nearly every clause carries operative information, and the semicolon-delimited structure keeps the tier rules separable. The ordering is inverted, though: three sentences of access gating precede the sentence that says what a regime read actually is, so the agent meets conditions before 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?

The definition covers what the reads contain, when they publish, who can see what, how parameters are honored per tier, and the return payload's shape and limits, which is more than enough for a read-only tool that also ships an output schema. Nothing an agent needs before calling 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 the baseline is 3; the description earns a bump by clarifying consequences the schema only states tersely — that a supplied date or time is silently ignored for signed-out callers, and that detail 'all' returns every read of the session while date selects another session. The distinction between 'accepted for compatibility' and 'actually honored' is meaningful added value.

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 names the resource and its contents precisely: 'market bias, pivot levels, a thesis and the level that would invalidate it, then a graded end-of-day recap at 16:15 ET', which is far more specific than the title 'Regime reads'. It does not, however, differentiate itself from similarly named siblings such as get_readings, read_the_board, or get_active_levels, so an agent must infer the boundary.

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?

Access-tier guidance is unusually explicit: unauthenticated callers get only the recap and any date/time is ignored, free accounts get the same, and paid plans get the latest read, changes, and all reads of a session for any date. This tells the agent exactly what it will receive under each condition, though it never states when to prefer this tool over a sibling for a given question.

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