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

Goes well beyond the annotations: it discloses that the call REPLACES the existing read unless append:true, exactly matching destructiveHint=true, and describes the write target (session card with coach read and badge) and rendering behavior (markdown renders). The grade rubric also documents judgment nuance (dropping load and finishing is not an E), which is behavioral context annotations cannot express.

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-loads purpose, destination, and the sibling distinction before diving into grade detail. Every sentence earns its place, but the whole thing is one dense block with rubric and edge-case guidance interleaved, which slightly impairs scannability.

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 write tool with no output schema, the definition supplies everything an agent needs: what is written, where it appears, replacement vs append behavior, parameter meaning, prerequisites, grade semantics, and the Analyze-turn exclusion. No meaningful gap remains.

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?

With 0% schema coverage, the description fully compensates: it defines date and title-as-disambiguator, explains append:true semantics, and gives a complete A..E grade rubric including edge-case interpretation. Notes content and markdown rendering are also covered, so every parameter's meaning is clear from the description alone.

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 and resource: "Write your read of one LOGGED gym session and grade it," and identifies where the output lands (session card). It explicitly distinguishes itself from set_activity_notes by explaining that a gym session usually has no activity row, so an agent can route correctly without opening either schema.

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 (naming a session by date, plus title when two were logged), when-not-to-use (on an Analyze-button turn the app saves the reply, so don't call this), a prerequisite (read get_strength_log and get_strength_progression first), and the sibling it replaces (set_activity_notes unreachable for gym sessions). Nothing is left to inference.

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