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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. Beyond this, the description adds rich behavioral context: tier-dependent behavior ('Hobby+ for prices; free tier gets the full structure... but prices nulled and redacted:true'), return-structure details (all_prices array sorted best-first, one row per book with last_update), and book-coverage quirks (DFS exclusions, Underdog two-way limitation). No contradiction with annotations.

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?

Five information-dense sentences with zero filler — every sentence carries distinct value (tiering, return contract, sibling differentiation, exclusions, filter intent). Slightly front-loaded with a parenthetical-heavy first sentence ('Hobby+ for prices; free tier gets the full structure...'), which takes effort to parse, but nothing is wasted.

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 complex tool with tiered access, no output schema, and 22 siblings, the description covers the critical gaps: it documents the return contract (best-first all_prices, per-row last_update, redacted pricing flag) where no output schema exists, explains conditional availability (DFS exclusions, Underdog limitation), and positions this tool among its get_* siblings. This is complete enough for an agent to know exactly what to expect.

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 60% (markets, bookmakers, include_links documented; sport_key and event_id bare). The description reinforces the bookmakers parameter's intent ('to shop only the books the user holds accounts at'), which mostly restates the schema's own 'to shop only those books.' It adds tier context that affects observable output behavior but no new per-parameter syntax or format guidance beyond the schema, so it neither compensates for the gap nor adds much incremental value.

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?

Clear verb+resource+scope: 'returns the single best American price across all comparable books' for each (market, player, line) tuple. Explicitly distinguishes from siblings by naming propline_get_event_ev as a companion and contrasting: '/ev says whether a price beats the no-vig fair line; best-line says which book pays the most.' Also details exclusions (DFS pick'em books) that separate it from generic odds tools.

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?

Provides explicit when-to-use and when-not-to-use guidance: it names the alternative (propline_get_event_ev) and articulates the decision rule for choosing between them. Also covers behavioral exclusions ('DFS pick'em books... are excluded; Underdog only at clean two-way lines') and usage intent for the filter ('to shop only the books the user holds accounts at').

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