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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description carries a lighter burden. It adds meaningful context: 'card' versus 'full' output behaviors, the direction field is the pattern's native side not the trade side, and that 'strengthTier is an ID-band label, not live chart state.' These are clarifying notes beyond what annotations provide and help an agent interpret results correctly.

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?

The description is a single, well-structured paragraph of about three sentences. It front-loads the core function (blacklisting all setups) and then packs in useful details (total counts, detail modes, filtering options, and critical constraints). While it is dense, there is no filler; every clause contributes meaning, and it remains understandable.

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 responsibility to explain what the tool returns. It covers 'full' (once each setup's playbook fields are enumerated) and 'card' (catalog fields only), and explains the semantics of the 'direction' and 'strengthTier' fields. It also states which filters are supported and the applicability constraint across chart intervals. For a read-only listing tool, the description provides sufficient context for an agent to invoke it and interpret results correctly.

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 60% (3 of 5 parameters have descriptions in the schema). The description compensates for this by explaining 'type' (FAN/TICK/ALL) and 'direction' (native side vs trade side), which are missing from the schema. It also explains 'detail' exactly as the schema does, and mentions the 'timeframe' constraint in the context of tick charts. This added explanation is helpful for correct invocation.

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 begins by stating the exact action and scope: 'List all 64 active LinReg setups (45 Fan -series + 19 Tick T-series).' This specifies a clear verb ('list') and a well-defined resource ('setups') with precise counts and types, distinguishing it from sibling tools like maatsii_get_setup which retrieves individual setups. It also introduces the 'detail' concept, which is central to the tool's output differences.

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 description provides clear usage context: it is for listing/browsing all setups, with an explicit hint that 'detail: card is a lightweight catalog for browsing.' It also gives a substantial caveat that TICK setups and tick-native Fan #34 apply only on 100T/1000T tick charts, which guides when to filter by timeframe appropriately. However it does not explicitly address alternatives like maatsii_get_setup for a single result, nor does it directly say when not to use this tool.

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