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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds useful context beyond that: Grade has no expiry date, it is the only surviving free-text field, and the migration date that moved everything else to facts. It does not explicitly restate that the default mode overwrites prior Grade, but the schema's mode description carries that.

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 core action and the format template, then the rationale. The 'three cancelled-race sections' anecdote is mild editorializing, but it justifies the architectural split in one clause and is not wasted space.

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 single-section mutation tool with no output schema and full annotation coverage, the description covers what is written, in what format, and what has moved elsewhere. A brief note on what the write returns or how it affects subsequent knowledge-base searches would close the last 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, and the description exceeds it by documenting the actual line syntax allowed in `content` (sport/level/populations with valid enum values), which the schema only calls 'the Grade lines'. The mode semantics are left to the schema, which handles them adequately.

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 precise verb+resource (set the athlete's Grade section of the athlete file) and specifies the exact content format with enum values for level and populations. It also explicitly scopes itself: 'That is ALL this tool writes now,' separating it cleanly from the fact tools in the sibling list.

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?

Names the alternatives explicitly (add_fact / update_fact / confirm_fact / retire_fact) and gives the condition that selects them ('a fact needs a horizon'). It also explains why Grade is the deliberate exception, so an agent knows both when to use this tool and when not to.

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