prepare_semantic_batches

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

With no annotations, the description carries the full behavioral burden. It hints that output goes to a separate new directory (implying the source is untouched), but says nothing about whether the directory must be absent/empty, whether existing files are overwritten, side effects on the semantic store, or permissions/rate considerations.

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 short sentence with no filler, and the key information (what is produced, where it goes) is front-loaded. It is efficiently written; its problem is omission, not verbosity.

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?

An output schema exists, so return values needn't be explained, but for a mutation-style tool with zero annotation coverage, 0% parameter documentation, and a crowded sibling set of semantic-store tools, this one sentence leaves an agent unable to call it confidently.

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 0%, so both required parameters (source_run, output_dir) are undocumented in structured data. The description only loosely gestures at them ('source-bound' for source_run, 'separate new directory' for output_dir) without stating expected formats, identifiers, or constraints.

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 verb ('materialize') and a resource ('semantic candidates') with a scope modifier ('source-bound') and an output location. However, 'materialize' and 'source-bound' are pipeline jargon, and the description gives no hint of how this differs from close siblings like initialize_semantic_store, inspect_semantic_store, or preview_semantic_patch.

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 guidance at all — no prerequisite state, no mention of what must precede it (e.g. an inspected run or initialized semantic store), and no alternative named. An agent must infer its place in the workflow purely from the tool name.

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