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

With only readOnlyHint and idempotentHint in annotations, the description carries real extra weight: no API key required, data freshness of 60-120 s, exclusions ('without stop and widened'), a 10-fixture cap, and a 10 calls/minute rate limit. Those are exactly the operational constraints an agent needs before choosing this tool.

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?

A single dense sentence that front-loads the key differentiator ('free sample without an API key') and then packs limits at the end. Nothing is redundant, though the parenthetical 'without stop and widened' is jargon that costs a re-read.

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 two-parameter read-only retrieval tool with no output schema, the description covers access model, freshness, result cap, and rate limit. It stops short of indicating what fields come back or what 'widened' means, which is the main residual 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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by identifying odds as the consensus and qualifying its staleness and exclusions, while the schema only says 'the consensus'. The league parameter gets no extra treatment beyond the schema's own enumeration.

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 concrete verb+resource pair: returns one league's consensus odds (kind=odds) or today's fixtures (kind=fixtures), explicitly framed as a free sample. The distinction from full-data siblings lies only in the word 'sample' and 'without an API key', so an agent can infer it differs from get_consensus/list_fixtures but is not told so directly.

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?

'A free sample without an API key' implies the usage condition (no key, quick peek), and the 10-call/minute limit implies this is not for bulk work. However, it never names get_consensus or list_fixtures as the full-data alternatives, so the agent must infer the routing itself.

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