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

No annotations are provided, so the description carries the burden of behavioral disclosure, and it does offer one piece: 'Key discarded' communicates that the input is not retained. But it says nothing about what happens on valid versus invalid shape, whether it returns a boolean, throws, or performs network access — leaving most of the behavioral surface opaque.

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?

Two short sentences, front-loaded with the core purpose and zero filler. The brevity is genuinely concise, though it trades away content completeness, which is penalized under contextual_completeness rather than here.

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 9-parameter tool with no output schema and no annotations, a two-sentence description is materially inadequate. It fails to explain the return value, the definition of a valid 'shape,' or how any of the nine parameters relate to the stated purpose, so an agent cannot invoke it correctly or interpret its result.

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 each of the nine parameters is individually described in the schema and the baseline would be 3. But the description references a 'key' that maps to no parameter at all, and it adds no guidance on how the Jira check relates to ref, url, city, feed, host, json, path, zone, or query — creating a mapping gap rather than adding meaning.

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?

The description names a specific verb and resource ('Check a Jira issue key shape'), which distinguishes it by name from sibling format-checkers like github-repo-shape and domain-shape. However, it never defines what a valid Jira key shape is, never states the result of the check, and does not reconcile with a schema whose nine parameters contain no Jira-key field — so an agent cannot tell which input is the key.

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?

There is no when-to-use, when-not-to-use, or alternative guidance at all. With a dozen sibling shape/format/URL checkers (github-repo-shape, figma-url-shape, domain-shape, normalize-url), the description gives an agent nothing to select this tool over others.

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