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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds useful extra context: one result per request user and optional filter ranges. However, the garbled phrase "passedFilter" and lack of details about return shape, errors, or rate limits keep this at a solid but not high level.

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 description is short and front-loaded with the main purpose and cardinality. It loses points for the awkward, unclear "Optional filter sets passedFilter" phrasing, which is not a clean expression of the filter parameter behavior.

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?

Given there is no output schema, the description gives only a minimal hint about return behavior (one result per user) and no shape or example. It also does not clarify how user identifiers should be provided or what happens for invalid or missing users, leaving an agent with meaningful gaps for a nested-parameter batch tool.

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 around 50%, with descriptions for the users array and minScore but not for filter type or the user object fields. The description adds the account/username dimension and repeats the filter ranges, but it does not clarify the crucial detail of how to specify a user (id vs username) or that filter requires both type and minScore when present.

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 clearly states the tool fetches scores in batch for linked accounts or Connect usernames and adds the valuable behavioral note "One result per request user." It does not explicitly name sibling tools, but the batch scope plus account/username coverage distinguishes it from the single-account score tools.

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?

The batch wording implies it is for multiple users, and the description says it covers both linked accounts and usernames, which signals usage context. However, it never mentions when to prefer connect_scores_by_account or connect_scores_by_username for single-user lookups, nor does it mention any exclusions or alternatives.

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