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

Annotations already declare readOnlyHint/idempotent/non-destructive, yet the description still adds genuinely new behavior: data is read from positions this account already recorded, not fetched from the store, so there is no latency or rate-limit exposure. It also states each row carries its evidence and that tracked competitors retain positions even on days they drop out of results, plus the account sign-in prerequisite with concrete login commands.

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?

The opening sentence is front-loaded and the body is organized as sets → provenance → usage → auth, with no filler. It runs slightly long, and the full sign-in command line is more instructional overhead than most callers need, but every paragraph still earns its place.

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 two-parameter read tool with no output schema, the description covers everything needed to call it correctly: the shape of both returned sets, why candidates may be empty, the data source and its staleness characteristics, and the authentication requirement. Nothing material is left for the agent to guess.

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 baseline is 3, but the description adds real meaning beyond the one-line schema text: include_observed is characterized as surfacing unpromoted 'candidates' ranked by how often they beat you, and the description clarifies that promoted competitors persist through zero-visibility days. That is more than the schema conveys on its own.

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 ('Who this extension competes with, measured across every keyword it tracks') and then splits the output into two named, distinct sets. It also names the sibling add_competitor as the thing that populates the roster, so an agent can separate it from get_extension, list_keywords, and the rest of the family without reading any 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?

'This is the tool for deciding who is worth promoting' gives a clear decision context, and the contrast with add_competitor implies the boundary between reading the roster and mutating it. It stops short of saying when NOT to use it (e.g. use get_keyword_ranks for a single term's positions) or that candidates require a deliberate include_observed opt-in for a reason.

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