project_memory

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: the notes are 'durable' and resurface via project_context 'in future conversations', and remove operates by index, signaling irreversible per-entry deletion.

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?

Two tight sentences, front-loaded with the persistence purpose, then the action syntax, then the content rule. Every clause earns its place with no filler.

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 4-parameter, no-output-schema mutation tool, the description covers purpose, action modes, parameter mapping, and the persistence behavior an agent needs. The only gap is the shape of the 'list' return (e.g. whether indexes are shown), which matters since remove relies on index.

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 only 25% (only path is documented), so the description must compensate and largely does: it binds 'add' to note and 'remove' to index, revealing the action-to-parameter mapping the schema does not express. path's directory semantics are left to the schema, keeping it from a 5.

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 resource (durable per-project notes) and enumerates the three action modes (list/add/remove), which lets an agent tell it apart from the many browser/process siblings. It does not name the closest alternative by comparison (project_context is mentioned only as the consumer), so it falls just short of a 5.

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?

Gives explicit content guidance — 'Save conventions, gotchas and verified commands — not temporary state' — which is a clear when-to-use plus a when-not-to-use. It stops short of naming a competing tool for ephemeral state, so no full routing is provided.

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