recall_project

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the reranker takes about 20 s per question and did not improve held-out recall, and covered hits return as references. It omits auth/prerequisite and return-shape details.

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?

Purpose is front-loaded, which is good, but the middle sentence is dense and the trailing 'Continue incomplete sources before making decisions' is vague and low-value. It is not padded, but not every sentence earns its place equally.

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?

For a 12-parameter retrieval tool with no output schema and 42% schema coverage, the description leaves significant gaps: several parameters (mode, needs) are undefined and the return/selection behavior is only glancingly described. Given the complexity, more disclosure is warranted.

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 only 42% across 12 parameters, so the description must compensate but only partly does. It explains local_reranker_profile/local_embedding_profile behavior, but leaves unexplained parameters like mode (the defaulted 'auto') and needs, which an agent cannot interpret from the bare 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?

The description names a concrete verb ('Find') and two resources ('original source evidence' and 'current reviewed memory'), so an agent knows this is a retrieval tool. It does not, however, distinguish itself from overlapping siblings such as search_project_memory or project_memory, leaving the boundary to be inferred.

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?

It gives one narrow piece of usage guidance (leave the reranker unset for a single-conversation project) and a vague directive ('Continue incomplete sources before making decisions'). It never states when to prefer this over search_project_memory, read_project_source, or project_memory, so the when-to-use logic is only implied.

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