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

Annotations already cover read-only/idempotent/non-destructive safety, so the bar is lower. The description adds genuinely useful behavior beyond that: a 30-minute refresh cadence and DraftKings scoring, which affect freshness and interpretation of projection/salary output. It doesn't mention auth or pagination limits beyond the schema's plan-limit note.

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?

Purpose is front-loaded, followed by the two-mode conditional, then a refresh caveat and scoring note. Every clause carries information (line slots, stat fields, salary, stack behavior); nothing is redundant or padded.

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 2-param read-only tool with full annotation coverage and no output schema, the description compensates by enumerating the returned fields (projection, shots, points, TOI, salary) and the fallback behavior without a team. An agent has enough to call it correctly and interpret results.

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 100%, so baseline is 3, but the description adds real meaning beyond the schema by specifying what supplying 'team' actually returns versus omitting it — the schema only says 'Team abbreviation'. That semantic effect of the optional parameter is valuable and not captured in structured fields.

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 ('NHL line combinations') and then delineates exact content per usage mode: forward lines F1-F4, defense pairs D1-D3, goalies, PP/PK units, plus stacks. An agent can distinguish it from siblings like invoke_nhl_line_matchups or invoke_nhl_projections without opening a schema, since the output composition is spelled out.

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 clear conditional guidance through the 'With team:' / 'Without team:' split, telling the agent exactly which call shape yields team-specific lines vs. the day's top stacks. It does not name alternative tools or state exclusions (e.g., when to prefer invoke_nhl_team_matchups instead), so it stops just short of a 5.

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