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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely new behavioral context the annotations cannot convey: it returns partial or no rank instead of inventing attention scores when volume data is missing, which tells the agent how to interpret gaps in output.

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?

Two sentences, zero filler, with the scoping restriction front-loaded ahead of the failure-mode disclosure. Nothing repeats the title or annotations.

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?

The honesty policy is well covered, but with no output schema and no parameter documentation, the description never says what a 'rank' or 'attention' value looks like, whether results are ordered, or how partial results are represented. For a tool whose entire selling point is a scoring output, that leaves a real gap.

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 description coverage is 0% for both parameters — limit and category appear as bare typed fields with only default/maximum/pattern. The description mentions neither parameter, so an agent gets no meaning for what 'category' values correspond to or how limit affects the ranking breadth.

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+resource (rank prediction-market attention) plus a hard scoping rule: only markets with an explicit public Robinhood volume signal. That distinguishes it from prediction_list_markets and prediction_get_market, which surface markets rather than ranking them, though no sibling is named explicitly.

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 coverage constraint implies when the tool is appropriate (you want attention ranking and accept partial results), but there is no explicit when-to-use statement, no exclusion of alternatives like prediction_list_markets, and no guidance on choosing this over a snapshot-style sibling.

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