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

Annotations already declare read-only, non-destructive, and closed-world behavior, so the bar is lower. The description still adds meaningful context beyond them: the operation is free, input is capped at 1 MiB, output at up to 100 items, and — most valuably — 'does not retain feed content' discloses a data-handling trait absent from 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?

Three short sentences, purpose front-loaded, with limits and exclusions following in descending importance. No filler or repetition; every clause earns its place.

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 two-parameter, no-output-schema tool, the description covers purpose, limits, and the key no-network/no-retention caveats. It stops short of hinting at the structure of the returned JSON, which an agent would need to consume the result, but nothing critical for invocation 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 0%, so the description must carry parameter meaning. It partially does: '1 MiB input' maps to the xml maxLength and 'up to 100 returned items' implies limit caps returned entries. It never clarifies the default of 50 or that xml must be raw XML text (not a path/URL), leaving the compensation incomplete.

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 with scope: 'Normalize one RSS 2.0 or Atom XML feed to stable JSON.' The single-feed scope and the input/output formats are unambiguous, and no sibling tool overlaps with feed normalization, so differentiation is not required.

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?

'Does not fetch URLs' is an explicit negative usage constraint that prevents a plausible misuse (passing a URL instead of inline XML). However, there is no statement of when to choose this tool over another or what to do with multi-feed batches, so the guidance is clear but not exhaustive.

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