code_graph_index

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

With no annotations, the description carries the full burden and does well: it discloses the indexing behavior, local SQLite storage, idempotency (upserts), and that 'force' is reserved. It doesn't cover failure modes or side effects beyond DB creation, but the provided behavioral details are substantial.

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?

The description is front-loaded with the core purpose, then efficiently covers parameter notes. Each sentence adds value; the constraints clause is concise and informative. Not overly verbose, though the param details could be slightly tighter.

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 covers the indexing behavior, idempotency, and DB location, but misses the required app_id parameter and says nothing about output/return values or potential errors. For a tool with no output schema or annotations, this leaves some gaps for the agent to handle.

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 description adds context for repo_root (directory to index), db_path (override location with defaults), and force (reserved/idempotent). However, app_id is a required parameter and is completely absent from the description, leaving the agent blind about its purpose. This is a notable gap given schema description coverage is 0%.

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 clearly states it indexes Python and JS/TS files into a local SQLite symbol graph, using a specific verb ('Index') and resource. It also differentiates from sibling read tools by saying 'Run once before the read tools.'

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 explicitly says to run once before the read tools, giving clear context for when to use it. It also mentions constraints (pure stdlib, no network/Postgres/external CLI) that help an agent decide, though it doesn't name specific alternative tools or state when not to use it.

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