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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), disclosing the auth requirement ('Authenticated via project API key'), status-transition policy (IN_PROGRESS_BUG after a code fix, FIXED only after confirmation), and that agentTraceability records CREATED/UPDATED Activity inline. It does not cover failure modes or what a partial patch does to unspecified fields, keeping it short of a 5.

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 the create-vs-update contract, then layers the workflow-specific guidance. Dense but every sentence carries operational value; the '/testchimp'-specific rules could be tightened without loss.

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?

No output schema and a 31-parameter nested schema mean the description should do more heavy lifting than it does. It covers the high-stakes decisions (create/update, status transitions, TASK_ISSUE labeling, auth) but leaves the majority of parameters and the merge semantics of a partial patch unexplained.

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 description coverage is only 6% across 31 parameters, so the description must carry the load. It adds real meaning for a handful — issueId formats, status enum, ignoreReason, labels vs source ('set labels=["TestChimp Implement"] (not source)'), severity, category, linkTargets for STORY/SCENARIO — but leaves most params (botId, assignee, dueDateMillis, environment, issueType, addLabels/removeLabels, source) undocumented in either place.

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+resource ('Create or update a TestChimp issue in the current project') and immediately distinguishes the create path from the update path via issueId presence. An agent can tell it apart from get-issue-details and list-issues 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?

Explicit branching rules: 'Omit issueId and pass title to create' vs 'Pass issueId ... plus patch fields to update.' It also gives concrete when-to-use policy for the /testchimp implement TASK_ISSUE and fix flows, including 'set FIXED only after user confirmation.'

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