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

With annotations only indicating readOnlyHint=false and idempotentHint=true, the description carries rich behavioral detail beyond those signals: partial-update semantics, status transition enforcement (backlog→in_progress→done|cancelled; blocked→in_progress), Grove-mode gates (in_progress requires ≥1 AC; done requires file-evidence on every AC + session_history), and the nuanced attemptCommit behavior (post-deploy probe auto-run, re-setting is a new attempt, empty string clears). This is exactly the kind of non-obvious behavior an agent needs.

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 dense but every sentence serves a purpose. It front-loads the core partial-update behavior, lists updatable fields compactly, then layers in validation rules and return value. There is no filler or repetition of schema details; the long attemptCommit explanation is justified because it captures semantics that appear nowhere else.

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 an 11-parameter update tool with no output schema, the description is thorough: it states the return format ('Returns the updated goal with all fields'), covers partial-update semantics, validation rules, Grove-mode constraints, and attemptCommit's special behavior. The schema already documents parameter types and defaults, so the description does not need to repeat them. Together with the schema, an agent has enough to call this correctly in most scenarios.

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 100%, so the baseline is 3. The description adds value beyond the schema by explaining the intent of attemptCommit (auto-running post-deploy probes, clearing with empty string), the validation logic around status transitions, and Grove-mode constraints on status changes. It also confirms the priority range (1-5). This goes beyond what the individual schema descriptions state, though the schema already defines each parameter.

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 specific verb and resource: 'Partial update of a goal', and immediately clarifies the partial-update semantics ('only the fields you pass are changed; omitted fields are untouched'). It enumerates exactly which goal fields are updatable, distinguishing it from sibling tools like goal-update-assumption or goal-update-criterion by focusing on the goal's own fields and explicitly stating the return value.

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 gives clear context for when the tool applies — updating any of the listed goal fields — and includes conditional rules (status transition validation, Grove mode gates). However, it never mentions alternatives or exclusion criteria, such as 'use goal-update-criterion for criteria' or 'do not use this for assumptions.' Usage is implied rather than explicitly routed versus sibling tools.

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