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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds a genuine auth constraint ('Requires repo scope'), which is useful. 'Wraps src/lib/voice-to-pr.ts' is an implementation detail of little agent value, and the blast radius of the operation (does shipping a spec create a branch/PR, or write files?) is not disclosed.

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?

Two short sentences, front-loaded with the core behavior and the caller's choice. The 'Wraps src/lib/voice-to-pr.ts' clause adds little for an agent and could be dropped 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?

This is a non-read-only, non-destructive tool with four params, 25% schema coverage, and no output schema, so the description has a lot of room to fill. It omits what actually gets created (branch, commit, PR, or issue contents), how the transcript is interpreted, and never reconciles the 'to_pr' name with the spec/issue-only behavior.

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 coverage is only 25%, so the description should carry more weight. It does explain the `as` switch (spec vs issue) and mentions the 'repo' scope, but three of four parameters (owner, repo, transcript) are left entirely to the schema, and the `as` explanation largely repeats the schema's own enum hint.

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 uses a concrete verb and resource combination ('Interpret a free-form voice transcript') and names the two outcome modes (spec or issue), which distinguishes it from siblings such as merjax_ship_spec and merjax_create_issue that produce only one of those artifacts. The name/behavior mismatch (it says 'to_pr' but only describes shipping a spec or creating an issue) keeps it from being fully unambiguous.

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?

It implies usage (when the caller has a raw voice transcript) and says the caller chooses the output via `as`. It never explicitly says when to prefer this over calling merjax_ship_spec or merjax_create_issue directly, and gives no prerequisites or exclusions.

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