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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered structurally. The description earns credit for one genuine addition beyond the annotations — 'Removing a collection keeps its items' — but it omits the equally destructive remove-items path, says nothing about idempotency_key semantics, permissions, or what happens to orphaned items after a collection delete.

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, front-loaded with the primary action, and the deletion caveat is placed sensibly. However, 'Guide: competitors' is cryptic filler that consumes space without informing, and the terseness is under-specification rather than efficiency given the schema's complexity.

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?

A tool with a five-variant mutation union, a required idempotency key and no output schema needs far more description than two clauses. An agent cannot determine from this text which mutations exist or how to shape them, so the definition is materially incomplete for the tool's complexity.

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 0% and the mutation parameter is a five-branch oneOf whose semantics (which action takes which fields, item vs. collection vs. title) are entirely undocumented in prose. The description does not explain workspace scoping or the idempotency_key requirement, leaving the caller to reverse-engineer a fairly intricate payload.

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 two activities (organizing research into collections and saving a reference) that roughly map to the create and save_reference mutations, but the tool's schema supports five distinct mutations (create, rename, delete, add, remove, save_reference). Renaming, adding and removing items are never mentioned, so the stated purpose covers only part of the resource space.

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?

'Guide: competitors' is a pointer to external documentation rather than a when-to-use statement, and nothing distinguishes this from siblings like competitor_research_list, competitor_ad_reference_save or competitors_save. There are no exclusions or prerequisites to steer selection.

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