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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavioral context: substring/case-insensitive matching with no semantic search, snippet-around-first-hit output, and the hard constraint that unindexed items are invisible to search. The indexing caveat is a non-obvious, consequential trait.

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 two modes are front-loaded and each sentence carries information, but the description is dense and somewhat run-on, packing search semantics, return shape, and the indexing caveat into contiguous prose. Nothing is wasted, though a bulleted mode split would read faster.

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?

With no output schema, the description correctly carries the burden of describing return values for both modes (matched fields + snippet; REF code, name, kind, file type, scope, indexed flag). Combined with access-scope and indexing caveats, an agent has everything needed to call and interpret it.

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 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it enumerates the searchable fields (name, REF code, extracted text) and clarifies the access scope for `organisationId` (org items plus projects you are a member of). The only thin spot is the exact format of the returned snippet.

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?

States a specific verb+resource (find/library items) and explicitly splits the tool into two modes: keyword search with `query`, full listing without it. It distinguishes itself from siblings by naming `traceable_library_index` and describing exactly what is searched (name, REF code, extracted text).

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?

Explicitly tells the agent when to use each mode (with vs without `query`) and, crucially, what to do when a search returns empty: list first and check the indexed flag, then run `traceable_library_index`. This is actionable routing guidance, not inference.

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