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

Annotations already declare destructive=true, idempotent=false, openWorld=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: selections are REPLACED (not merged) and previously cached access is invalidated, which tells the agent exactly what state is destroyed. It omits what a version mismatch returns and whether authorization is required.

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?

Four short sentences, zero filler, and the core action is front-loaded before the '.' rule and the non-sync caveat. Every sentence adds a distinct fact an agent cannot get from structured fields.

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 destructive, non-idempotent mutation with no output schema and 20% param coverage, the description covers replacement semantics and cache invalidation but says nothing about failure modes (version conflict), authorization, or what the caller gets back. It is adequate to attempt the call but not to anticipate its outcome.

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 only 20% (just idempotency_key), so the description carries real weight. It does explain two non-obvious semantics — the '.' value selecting a whole repository and expected_version driving replacement — but leaves company, environment, sources structure, repositoryId vs repository, and folders paths entirely to the schema.

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?

States a concrete verb and resource: choosing branches/commits and allowed folders for GitHub sources, and explicitly distinguishes itself from the sync sibling with 'Does not sync code.' It never names summer_github_sources_read or summer_github_sources_sync directly, so the sibling routing is implicit rather than explicit.

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?

'Does not sync code' is a useful when-not-to-use signal versus summer_github_sources_sync, and 'Replaces selections with an expected version' hints at the guarded-update workflow. But there is no explicit guidance on when to call sources_read first, when to run sync after saving, or how to obtain the required expected_version.

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