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

Annotations only declare readOnlyHint=true, so the description adds real value by disclosing that matching is both lexical and semantic ('finds what the user means, not just exact words') and that results carry object_ids for follow-up. It stops short of describing ranking, pagination, or behavior when nothing matches.

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?

Front-loaded with the core purpose and matching semantics, then usage condition, then the edge case. The parenthetical enumeration of text-bearing object types is slightly verbose but does real work in scoping what semantic matching covers.

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 compensates by explaining what comes back (matching objects with their object_id) and how to use it. Combined with the type caveat and the when-to-use condition, an agent has everything needed to call this correctly.

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 goes beyond the schema on the 'type' parameter by warning that saved chat replies are type 'chat' rather than 'note' — a value-level nuance not present in the schema text. 'limit' is left entirely to the schema.

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 and resource ('Search the user's graph') and immediately clarifies the matching mechanism (name/description term match plus semantic matching over text-bearing objects). This distinguishes it from list_graph_objects, get_graph_object, and the many source-specific search_* siblings.

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 states the triggering condition — use it 'to find a specific thing they mentioned ... when you don't have its object_id' — and routes the agent to the natural follow-up (get_graph_object) once an id is returned. It also gives a concrete when-not/edge case: chat replies are type 'chat', not 'note', so search without a type or with 'chat'.

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