agtmem_search

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

Annotations already mark readOnlyHint=true, so no extra safety disclosure is needed; the description adds useful behavior: RRF-merged hybrid search, snippet-only results, and exclusion of superseded notes. These details go beyond what annotations or schema state.

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?

Three short sentences cover purpose, output, filtering, and usage context with no filler. Key behavioral facts are front-loaded before the usage recommendation.

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output schema, the description supplies the essential return information ('short snippets with ids') and a key filter ('Superseded notes are excluded'). Combined with schema-described parameters and the read-only annotation, an agent has enough to call it correctly, though an explicit nod to alternatives like agtmem_find would complete the picture.

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 descriptions already cover type, query, and scope, and limit has a default, so the parameter burden is largely carried by the schema. The description adds no parameter-level detail, but with roughly 75% coverage the gap is not critical; this is an adequate baseline.

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 identifies the operation ('Search long-term memory') and resource, augmented by the retrieval mechanism (hybrid FTS5 + trigram, RRF-merged). It also conveys the output form ('short snippets with ids'), so an agent can distinguish it from a full read tool. It does not explicitly differentiate from agtmem_find, which costs the fifth point.

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?

'Use this first when resuming work on a project' gives concrete situational guidance and implies this is the entry point before reading or writing. It lacks an explicit when-not-to-use or named alternative, so it stops short of full routing guidance.

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