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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds material context beyond them: it discloses that invalid input never raises a protocol error and instead returns a structured {"error": ...}, and that retrying after a fix is always safe. It also flags the tool as free, which matters for an agent selecting among siblings.

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 platform list, then usage, then exclusions, then error contract — a sensible progression. It runs slightly long, with the error/retry sentence and the 'FREE' marker competing for attention, but no sentence is filler.

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 one-parameter read-only checker with an output schema, this is more than sufficient: scope, exclusions, example input/output, and error behavior are all present, so an agent can call it correctly on the first attempt.

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 a single parameter at 100% schema coverage, the schema already carries the semantics; the description still adds value by showing a concrete input shape ({"text": "<post>"}) and the corresponding result structure, making the call pattern obvious. It stops short of covering edge cases like empty text or non-string input.

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 ('check a post against every major platform's length limit at once') and enumerates the platforms covered, so an agent can distinguish it immediately from analyze_writing, headline_analyzer, and reading_time.

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 names the usage moment ('use before posting, to catch truncation') and rules out the two adjacent siblings by name: 'not for readability (analyze_writing)' and 'not for reading duration (reading_time).' 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.