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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, yet the description adds substantial non-structured behavior: the index only moves when a new bond prices, there are exactly 13 events spanning 2025-05-19 to 2026-07-24, and it discloses the per-event payload (date, level after event, bp change, notional added, per-bond pull attribution) including the pull_bp formula and the guarantee that pulls sum to the event delta.

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?

Dense and well front-loaded: purpose, then mechanics, then filters, then the negative constraint. The headline statistics (517.7bp inception, 410.0bp trough, 432.3bp now, -85.4bp net) are snapshot values that duplicate what the tool returns and will drift out of date, which is the one place sentences do not fully earn their place.

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?

With no output schema, the description carries the return-shape burden and does so: it enumerates the per-event fields, explains the pull attribution math and its summation property, and bounds the dataset in both time and count. An agent can call this correctly and set expectations without inspecting any other artifact.

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; the description goes slightly beyond by explaining the intent behind each filter — since shows "only that window" and ticker shows "that issuer's pricing events" (i.e., events that added that issuer's bonds, not events where it merely existed). It stops short of adding new syntax or edge-case behavior not already in the schema.

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?

Opening line states a specific resource and framing: "The index history" for NCSX-IS, with an explicit contrast to the level-lookup siblings ("how did NCSX-IS get to its current level" rather than "what is the level"). It also pins down the domain model (event-driven replay of 13 pricing events) so an agent can distinguish this from ncsx_index, ncsx_latest, and ncsx_marks.

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 the selection condition versus the alternative (history vs current level), gives concrete filter recipes for both parameters, and adds a negative instruction — "There is no daily series and no traded level — do not describe these as closes or weekly moves" — which prevents the most likely misuse. Nothing about when to reach for this tool is left to inference.

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