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

Annotations only say readOnly=false and destructive=false, so the description usefully fills in that this is a partial-field update (any field not sent stays as-is, implied by the field-by-field enumeration) and warns that 'remove takes a derived term out for good', flagging irreversibility that the annotations downplay. It doesn't mention permissions, validation errors, or whether name changes affect existing references.

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 sentences, both dense with information: the first enumerates the mutable surface, the second covers the side effect and scope override. No filler, and the most consequential fact (dismiss = stop tracking) is placed before the scoping note.

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 mutation tool with no output schema and full schema coverage, this is nearly complete: it says what can change, what a status change implies, and how the Space scoping resolves. The remaining gap is the absence of an explicit alternative route (untrack_competitor / track_competitor) among its many siblings.

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 100%, so the schema already defines all three parameters, including nested brandTerms with add/remove. The description adds real semantic value for mindshare – brand terms are 'the words the copy check will not let generated copy use' and removal is permanent – but does not describe the format expectations for domains or the competitor_id source. Baseline 3 applies when the schema does the heavy lifting.

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 uses a precise verb (rename/change/move) plus the resource, and enumerates every mutable field: name, domains, tracked/dismissed/suggested status, and brand terms. It does not explicitly name the nearest siblings (untrack_competitor, track_competitor, refresh_competitor), leaving the boundary between 'set status=dismissed' and 'untrack_competitor' implicit.

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 clearly explains the effect of one key mode ('Dismissing stops tracking and keeps it from being suggested again') and gives explicit routing for the Space-scoping decision, pointing at set_active_space vs. passing space_id. Still missing an exclusion like when to prefer untrack_competitor over setting status, so it's clear guidance without complete alternatives coverage.

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