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

Annotations only cover read-only/idempotent safety; the description adds the gated behavior an agent actually needs: Premium required with 403 `plan_required` + `details.feature`, company-admin-only with 403 `forbidden`, JWT/company mismatch -> 404, bad range -> 400 `invalid_range`. It also discloses the metric definition (first in-progress -> done, median/p85) and the partial-data `cycle_measured` of `cycle_total` caveat with an explicit no-extrapolation instruction.

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?

Front-loaded with scope, then auth, then semantics, then output interpretation – a sensible order with no filler sentences. Minor redundancy: the title is restated verbatim and the "measured `cycle_measured` of `cycle_total`" phrasing appears twice in slightly different forms.

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 no output schema, the description still tells the agent what comes back (`projects`, `people`, `agents`, `people[].done_cards`/`done_points`, `unassigned`, cycle median/p85) and what their absence means. Combined with the auth and error contract, an agent has everything needed to call and report on it correctly.

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 would be 3, but the description adds decision-level semantics: the range defaults to the last 30 days and should only be overridden when the user specifies one, and `compare` adds the previous period. That is usage meaning the schema's type/default text does not convey.

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 specific resource and scope ("Flow numbers across every project of the company, with people and agents") and explicitly relates it to the sibling: "Same numbers as `get_project_insights` pooled over every live project, plus `projects`, `people` and `agents`." An agent can distinguish it from get_project_insights without opening either 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?

Gives concrete when-to-use rules: company-wide rollup vs. the per-project sibling, pass `from`/`to`/`compare` only when the user names a range, and CSV exports are web only. It also names the failure modes that change the answer (non-admin -> absent people/agents -> say so, never invent).

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