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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds genuinely new context: grading uses fixed deterministic rules with no AI model calls, the paid endpoint returns identical output, and results are informational only and not financial advice. It does not say how the tool behaves when optional excursion/stop fields are omitted, which is the main remaining gap.

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?

One dense but front-loaded block: the 'FREE rule-based trade grade' qualifier and the tool's identity come first, followed by the graded dimensions. It is long but nearly every clause names a distinct capability or check. Minor cost is the tail clause about the paid endpoint and the disclaimer, which could be trimmed.

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 16-parameter analytical tool with no output schema, the description successfully conveys the shape of the result (efficiency scores, R-multiple capture, compliance flags) and the deterministic grading basis, which is what an agent needs to decide to call it. Missing only the edge-case behavior when optional benchmark inputs are absent.

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%, so the baseline is 3; the description earns a bump because it maps parameters to grading logic - entry/exit efficiency (entry_price/exit_price), stop-loss placement versus empirical ATR/MFE/MAE benchmarks (stop_distance/mfe_points/mae_points), R-multiples and risk checks (account_size), and rule compliance such as rollover window and time-stop (entry_utc_hour, minutes_held). This tells an agent which optional fields materially affect the score, which the schema alone does not.

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 ('scores entry/exit efficiency, stop-loss placement, R-multiple capture, rule compliance') and names the exact dimensions graded, so an agent knows precisely what the call produces. It also distinguishes itself from the paid /v1/paid/council_grade endpoint. However, it never distinguishes itself from the closest sibling tool, trade_postmortem, which appears to cover overlapping territory.

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?

The leading 'FREE' and the note that the paid endpoint returns the same grade imply 'use this instead of the paid variant', which is useful routing context. But there is no explicit when-to-use/when-not guidance relative to trade_postmortem or position_size, and no statement of prerequisites or what minimum inputs are needed for a meaningful grade.

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