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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious context: bot-tagged traffic is excluded from the activity summary at ingest unless include_bots is true, which changes how the returned data should be interpreted. It does not cover behavior when the external_id is unknown (empty result vs. error).

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, front-loaded with the lookup-key distinction and then the bot caveat, with no filler. The only blemish is referring to the operation by an internal method name ("GetByExternalId") rather than the tool name an agent will actually call.

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 an output schema present, the description need not explain return values, and annotations cover safety; what remains is the lookup-key rationale and the bot-filter caveat, both supplied. The gap is behavioral edge cases (missing profile, whether project_id is effectively mandatory) for an otherwise simple three-parameter read.

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 only 33%, but the description compensates for the two undocumented parameters: external_id is defined as the application-assigned end-user id, and include_bots is tied to the bot-exclusion behavior. project_id, the one schema-documented parameter, is left entirely to the schema, and no parameter is stated as required despite an empty required list.

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?

"GetByExternalId returns a single user profile looked up by the external_id your application assigned" gives a specific verb (returns/looks up) plus resource (single user profile) plus the exact lookup key. It also distinguishes the key from pug's internal profile id, which is what separates it from the plain get_profile sibling.

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 description makes the selecting condition explicit: use this when you hold the application-assigned external_id rather than the internal profile id. It does not name a concrete alternative tool or state exclusion conditions (e.g., what to use when only an internal id is available), so it stops short of full when/when-not routing.

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