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

Beyond annotations, the description reveals multiple non-obvious behaviors: missing symbols are omitted, each symbol counts toward a daily limit, over-25 requests are rejected outright with batch_too_large, duplicates are collapsed through normalization, and Pro-tier data is 'precomputed' with no live AI cost. It even provides a response invariant formula, which is far more behavioral detail than annotations supply.

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 long but well-organized with clear paragraphs and front-loaded purpose; every section covers a distinct operational concern (main semantics, tier details, exclusions, and the duplicates invariant). It repeats the over-25 rejection that already lives in the schema, which is a small efficiency loss, but the structure and packaging is strong.

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 batch endpoint with tier differences, daily limits, normalization behavior, and output shape quirks, this description leaves nothing an agent needs to infer. It enumerates what's included, explicitly lists what is NOT included and which sibling to call instead, and even describes output-level invariants. The presence of an output schema lowers the burden on explaining return values, but the description still covers the non-obvious delivery semantics.

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?

The schema already covers the basic limits and rejection behavior for the symbols parameter, so baseline is at 3. The description adds meaningful symbolic semantics: how duplicates are collapsed via 'case-folding, share-class aliasing e.g. BRK.B->BRK-B' and how requested/missing/duplicates relate in the invariant. That adds real value beyond 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?

The description opens with a precise verb constraint: 'Batch stock data for up to 25 symbols in a single call', and immediately distinguishes itself from get_stock by clarifying it returns 'the same fields get_stock returns' and is 'a true batch version, not a thinned-down scan.' It also names its result shape, so an agent knows exactly what this tool is and what it produces.

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 gives explicit when-to-use and when-not-to-use guidance: if you need more than 25 symbols, 'split a larger list into multiple calls; if you need stance_signals, get_stock(symbol); if you need full AI text/news context, get_stock_research(symbol).' It also notes tier availability, making the routing decision complete.

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