read_mcdev_artifact_source

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

With no annotations, the description carries the full burden and does so thoroughly: returns complete original UTF-8 text including BOM plus SHA-256 of original bytes, no truncation, unresolved or blocked results never contain source, no rendering/validation/mutation/live execution, execution readiness unknown, bounded checks are not atomic against concurrent filesystem mutation, and auth contents and logs are never read. These are non-obvious safety and output-shape facts an agent could not infer from schema or name.

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?

Nearly every sentence carries real information and the read-only/no-source-on-failure constraint is front-loaded, but the delivery is a dense run-on of fragments and negations that is hard to parse on first read. It would benefit from grouping output shape, blocking rules and validation handoff into separate statements.

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 complex, no-annotation, no-output-schema tool, the description covers output format, failure behavior, blocking rules, safety limits and the validation handoff the host must perform. The remaining gaps are the seven undocumented parameters (identity, root, credential, bounds) that an agent must resolve purely from schema.

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 22% across 9 parameters, and the description meaningfully explains sourceRole semantics (resolved email companions only, no arbitrary filenames or paths) and constrains metadataType to bounded htmlemail/templatebasedemail layouts. But workspaceRoot, rootKind, credential, businessUnit, externalKey, maxDepth and maxEntries receive no explanation anywhere, so the description only partially compensates for the coverage gap.

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 ('read-only full-text editable-source handoff for one qualified query, script or bounded asset-email identity') and enumerates the metadata types, and it explicitly distinguishes itself from path-based readers ('never a caller-supplied file path'). The phrasing is dense and jargon-laden, but an agent can tell what it retrieves and what it does not.

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?

Gives concrete use conditions and blockers: exactly one editable companion required, multiple companions need an explicit sourceRole or are blocked, sourceRole applies only to resolved email companions, email html requires validate_sfmc_html, SQL validation not established. It routes the agent toward validate_ssjs/validate_sfmc_html/validate_ampscript, though it names them as capabilities to discover rather than as named sibling tools.

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