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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, and the description goes well beyond them: it clarifies that query only filters tickers, that offset/limit page the published order rather than re-sorting it, and that a page is not the full market population. It also warns how Signal Book rank should be interpreted (attention, not expected return) and points at /items and /metric_metadata for exact rows and clocks.

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?

Use case and exclusions are front-loaded, followed by clearly labelled Selection, Presentation, and Evidence blocks. Every sentence carries an actionable constraint; there is no filler.

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 an output schema present, return values need no explanation, and the description still covers usage, exclusions, parameter behavior, result interpretation, and where to fetch exact rows/metadata. An agent has everything needed to call and correctly interpret this tool.

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 the baseline is 3, and the description earns a bump by consolidating the interaction between query and pagination: query filters symbols and offset/limit walk the existing published order without sorting, plus a shortlist-length preference. Much of this restates the schema, so it is helpful but not fully additive.

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 ('the prepared market board or assets ranked for analytical attention') and gives a concrete user phrasing example, so the agent knows it returns an attention ranking rather than raw market data. It explicitly excludes research_briefing, gainers rankings, and buy/sell advice. It does not, however, differentiate from the very close sibling research_show_markets, which is a real gap in sibling distinction.

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?

Explicit when-to-use ('when the user wants the prepared market board...'), explicit when-not ('Do not use for published show content, a biggest-gainers ranking, or buy/sell recommendations'), and it names the alternative (research_briefing) that handles the excluded case. It also gives a selection preference ('prefer a small requested shortlist'), leaving nothing to inference.

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