start_file_review

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond annotations: it restricts input to 1-100 explicitly named UTF-8 text/source files and retains an exact hashed snapshot in memory for later send_followup calls. This stateful follow-up behavior is valuable context not available from the schema or annotations.

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?

One dense sentence that front-loads the action, states the key constraints, and discloses the follow-up snapshot behavior without filler. Every clause adds useful information and nothing is redundant with the schema.

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?

The description is adequate for a basic first call: it states the file constraints, follow-up capability, and safety. However, important operational context is missing: how to retrieve the initial review result, whether the call returns a task handle, how to choose a profile, and what counts as 'explicitly named' (e.g., no globs or directories). With no output schema to fill these gaps, completeness is only moderate.

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?

The schema has 0% description coverage, so the description must carry parameter meaning. It only clarifies input_paths semantics (explicitly named UTF-8 files, 1-100) and says nothing about how to write task, what profile affects, or how max_output_tokens behaves. The enum and bounds in the schema help marginally, but most parameters remain unexplained.

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 states a specific verb and resource ('Start a follow-up-capable review') and adds precise input constraints (1-100 explicitly named UTF-8 text/source files). It hints at a paired lifecycle by mentioning send_followup and the hashed snapshot, but it never directly contrasts the sibling review_files, so the differentiation is implied rather than explicit.

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?

The description implies this tool is for reviews that need follow-up ('follow-up-capable ... for send_followup'), so an agent can infer when to select it. However, it does not explicitly say when not to use it or name the one-shot alternative review_files, leaving the routing decision partially to inference.

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