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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: 'selection is a preview, never applied', 'Server owns as-of time', the resource_limited condition at 1,000,000 pairs, 'Other rendered views are explicitly unavailable in MCP, not missing athlete evidence', and hard exclusions ('no Strava, writes, automatic upload or strategy application'). 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?

Dense and front-loaded with purpose before routing. Nearly every sentence earns its place given the tool's complexity (six query modes, parameter rejections, resource limits, sibling routing). Minor deduction for recapping schema content ('Required query' enum list, 'Paged queries default offset 0/limit 20') which duplicates structured fields.

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 tool with six query modes and complex parameter interactions, the description is remarkably complete: sibling routing, pagination behavior, insights-specific rules, resource-limit semantics, safety exclusions, and semantic caveats ('Stored readiness is not current fitness'). Output schema exists, so return values need no description. Nothing an agent needs to call this 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 80% and the schema already documents defaults and per-parameter rejection rules, so baseline is 3. The description adds genuine meaning beyond the schema: the interplay between query modes and parameters ('insights rejects offset, limit and course context'), the effect semantics ('selection is a preview, never applied'), and the six bounded insight families. Slight redundancy with schema on pagination defaults keeps it below 5.

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?

Opens with a specific verb+resource: 'Read an existing USRProf or uploaded USRProf source artifact' with explicit scope exclusions ('without reconstruction, scope replacement or model activation'). It clearly differentiates from siblings like import_profile_attachment, get_artifact, and the goal/planning tools by declaring itself 'canonical inspection' and listing what it is not.

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?

Explicitly routes to alternatives with conditions: 'first use import_profile_attachment with explicit upload permission if host file handoff is available; otherwise offer the browser upload page immediately.' It also sets a boundary against goal/planning tools ('not these observational results as a finish-time prediction') and warns against substituting raw-file commentary. No inference required.

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