Session Briefing

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

Annotations already declare readOnlyHint=true and idempotentHint=true and the description's 'loads/returns/assembles' language is fully consistent with them, so there is no contradiction. The description adds real behavioral value beyond the annotations: the empty-project vs. project-set branches, the aggregation of four data sources, and the discoverability convention shared with vault_health() and worker_status(). It does not cover failure behavior for an invalid project slug, but that is minor for a safe, read-only call.

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 with the purpose front-loaded, followed by the two parameter-dependent branches and a cost comparison. Every sentence earns its place — including 'replaces 3-4 manual calls,' which conveys value, and the sibling mention, which conveys response-shape parity — with no redundancy.

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 single-optional-parameter, read-only, idempotent tool with an output schema, the description covers when to call it, what each branch returns, and how it relates to alternatives. The only gaps are minor: no statement of behavior on an unknown project slug and no note on data freshness/caching for the aggregated git and lesson data.

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% — the schema already explains the `project` slug format, the empty-string meaning, and even notes there is no `days` argument. The description's 'without a project / with a project' phrasing mirrors the schema rather than adding new semantic content, so it lands at the high-coverage baseline of 3.

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 opens with a concrete directive — 'Call at the start of every new session to load project context' — then details the two behavioral branches (project list vs. assembled briefing of tasks, lessons, git activity, health). It distinguishes itself from the vault_* and worker_status siblings by explicitly naming vault_health() and worker_status() and by describing aggregation semantics no sibling offers.

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 gives an explicit trigger condition ('start of every new session') and frames the tool as replacing '3-4 manual calls,' which tells the agent when the aggregated call is preferable. It names vault_health() and worker_status() for the discovery-parity case, but it never states an explicit when-not-to-use condition — e.g., what to call when only one slice of context (git activity alone) is needed.

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