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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: filters combine with AND logic, crossover operations evaluate against today's bar, screening runs on real-time data, and market_cap_basic is in absolute ₹ rather than crore — the last one prevents a serious misuse.

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-loaded with purpose and sibling routing before the DSL details, and nearly every sentence carries load. The FIELDS block is long but it is a required vocabulary list, so the bulk is justified rather than padding.

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 should ideally say what a result row looks like, but it does cover the inputs thoroughly (filters DSL, operations, field vocabulary, units, example, limit/columns/sort exist in schema). An agent has everything needed to construct a valid call; only the return shape is left implicit.

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 80% (baseline 3), and the description goes well past it for the hardest parameter: it defines the {left, operation, right} shape, enumerates the valid operations with the special case that in_range takes [min,max] and crosses_* mean crossover today, and provides a large whitelist of legal field names plus a worked example. The ₹-vs-crore units warning for market_cap_basic is exactly the kind of semantics the schema cannot express.

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 (screen) plus resource (Indian stocks), the axis (technical indicators) and enumerates the indicator families it covers. It explicitly names the sibling it is not (screen_stocks for fundamental screening), so an agent can route between the two without opening either schema.

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?

Gives a clear routing rule: technical indicators here, fundamentals via screen_stocks. It does not mention other plausible-looking siblings such as run_preset_screen, scan_movers, or screen_tapetide_scores, so the agent must infer those boundaries on its own.

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