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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavioral context beyond them: the exact ranking formula (importance 1-10, coverage bonus, -1 per 12h stale, one slot per ticker), the summary_state lifecycle (published/stale/preparing), pagination via next_cursor, and the card fields returned. This is well past the lower bar annotations set.

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 the resource definition, then mode behavior, card fields, routing, and sibling comparison. Dense but essentially every clause carries actionable information; the only minor cost is that it reads as one long block rather than discrete scannable statements.

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 3-param read tool with full annotations and an output schema, the description covers scope, mode semantics, ranking behavior, lifecycle states of summary_state, pagination, routing to the detail tool, and a research-not-advice disclaimer. Nothing an agent needs to call it correctly is missing.

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, but the description adds real meaning: it explains what 'top' actually computes (48h window, importance scoring, coverage bonus, decay) and that 'latest' should be followed via next_cursor. It goes beyond the terse enum default notes without fully specifying cursor semantics beyond 'follow next_cursor'.

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 resource with a precise definition ('market events that two or more publishers reported, each summarised by AlphAI from its articles') and distinguishes itself from siblings by naming alphai_trending (single-article ranking) and pointing to alphai_story for the full read. An agent can tell exactly what this returns without opening the 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 explicit when-to-use guidance for both modes ('list=top ... use it for what matters today'; 'list=latest pages every story newest-first'), names the alternative (alphai_trending) with the condition that separates them (events with independent coverage vs. single articles), and routes to alphai_story by story_id for detail. Nothing is left to inference.

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