index_code

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety and repeatability are covered. The description adds one genuinely useful fact beyond them: raw source is not persisted, so index-backed lookups will not surface file contents. It still omits where the index is stored, how expensive a build is, or what happens on a partial/failed index.

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, action first and the storage caveat second. Nothing is wasted and the lead clause front-loads the operation.

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?

Annotations cover the safety profile and there is no output schema to explain, so the bar is modest. However, for a tool that is the prerequisite for the map_* and symbol-lookup family, the description never states that dependency, prerequisites, or cost, leaving an agent to guess when it fits in a workflow.

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?

There is a single parameter (repo_path) with 0% schema description coverage, so the description carries the burden. 'For a repository' loosely maps the parameter to a repository target, but it gives no path format, relativity, or remote/URL guidance, leaving the only required argument underspecified.

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 gives a specific verb+resource pair: 'Build or update the local symbol map for a repository.' It is clearly distinguishable from read-only consumers like find_symbol or search_code. It stops short of explicitly naming which sibling tools depend on this index, so it is clear but not maximally differentiated.

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: nothing says this must run before map_find_symbol/map_dependency_graph, whether it is safe to re-run, or when it should be refreshed instead of supplemented by search_code. The agent must infer usage from the name alone.

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