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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false), lowering the disclosure bar. The description adds genuine value beyond annotations by disclosing two non-obvious behaviors — results are bounded/truncated excerpts and content is redacted per retention policy, plus a visibility filter agents would not assume on a list call. No contradiction, though 'canonical retention' is jargon-heavy.

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?

A single front-loaded sentence in which every phrase pulls weight — 'List' + 'SourceContent' carry the core action and the two qualifier clauses add behavioral precision without fluff. Nothing redundant.

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 browse/list tool with an output schema covering return values and annotations covering safety, the description covers purpose, scoping (visibility), and a surprise behavior (excerpt/redaction). The main omissions — explicit routing against get_source/search siblings and the basis of the visibility filter — are usage-guidance matters rather than gaps that would block a correct call.

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?

At exactly 50% schema description coverage, the description should compensate for the undocumented sort, limit, and offset parameters, but it adds zero parameter-level meaning. The undocumented params are partly self-explanatory via property names, enum values, and min/max/default constraints, but nothing clarifies query semantics, the meaning of 'exact' on sourceType, or offset pagination behavior across calls.

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 pair ('List visible SourceContent') with two behavior qualifiers — 'bounded excerpts' and 'canonical retention redaction' — that go beyond the title 'List sources.' The 'visible' filter adds scope but its determinant (permissions vs. retention) is left undefined, and the description never names how this differs from the decision_log_get_source or decision_log_get_source_decisions siblings.

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?

No usage guidance of any kind. The description never states when to browse via list_sources versus decision_log_get_source (single source fetch), decision_log_get_source_decisions, or decision_log_search_decisions, nor does it give a when-not-to-use. The browsing use case is left entirely to agent inference.

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