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

Goes well beyond readOnlyHint/openWorldHint=false: discloses ordering (relevance + recency), the exact per-hit shape (snippet with <mark>, score, scopeKey/scopeName/foreign), empty-result semantics, per-project access control for guests, and the paid-plan + non-project-scoped credential prerequisite. It also warns that foreign hits are reference-only, not this repo's convention.

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 and scope are front-loaded and no sentence is filler, but the single dense block piles parenthetical asides (the workspace default warning, the folder-name caveat) into one unbroken paragraph. Slightly long for what could be a lead sentence plus bullets.

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 six undocumented params, no output schema, and only two annotations, the description must supply both parameter meaning and return shape — and it does, including ordering, empty results, and hit field names. Nothing an agent needs to call this correctly is missing.

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 0%, so the description carries the full burden and does: query (empty → []), scope (client's project folder name, stable), limit (1-50, default 25 — which also corrects the schema's meaningless numeric bounds), git_remote (output of `git remote get-url origin`), crossProject, and workspaceId including the default-workspace caveat.

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?

Opens with a specific verb+resource in the first clause ('Busca en la memoria del agente ... full-text'), and immediately scopes it to a project/repo via `scope`, which separates it from broad siblings like mem_context or mem_save. An agent knows exactly what this returns without opening the schema.

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 concrete selection conditions: crossProject for workspace-wide lookup, git_remote when the local folder name differs from the clone, and workspaceId with a pointer to list_workspaces for enumeration. It stops short of an explicit 'use mem_get instead when you already have an id' style exclusion against siblings, so not a full 5.

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