index_paths

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

With no annotations at all, the description must carry the full behavioral burden, and it does disclose real traits: ignore-file support with glob syntax, and that .claude/worktrees are skipped by default. However, it never says whether indexing overwrites or merges existing entries, whether re-indexing is expensive or long-running, or what happens to previously indexed paths that disappear. For a mutating, potentially costly operation, those omissions matter.

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 core purpose is front-loaded, which is good, but the bulk of the text is spent on three example glob patterns that restate an already-familiar .gitignore convention. That space would be better spent on the undocumented 'mode' and 'paths' parameters. Efficient in tone, misallocated in emphasis.

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 the definition is still not complete enough to call correctly or safely. The single most decision-relevant input ('mode') is entirely opaque despite having a default, and there is no indication of cost, idempotency, or effect on existing memory. The ignore-file documentation is thorough, but it answers a secondary question.

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% for two parameters, so the description must compensate and does not. 'mode' has a default of 'incremental' with no enum and no explanation of what other modes exist or what incremental actually means, and 'paths' (nullable array) is never described — the agent cannot tell whether omitting it indexes everything or errors. All the parameter detail provided concerns a file format, not the inputs.

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 opening sentence states a concrete verb and resource: 'Register and index Markdown directories into project memory.' That is specific enough to distinguish it from all listed siblings (secrets, notes, entities, health), none of which deal with indexing. It stops short of 5 because it doesn't state scope crisply (whole project vs. selected paths) beyond what the parameter list implies.

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 explicit when-to-use or when-not guidance, no mention of how this relates to semantic_search or recent_context, and no stated prerequisites. The only routing information is implicit domain overlap ('project memory'). An agent gets no help deciding when indexing is warranted versus unnecessary.

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