upsert_milestone

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

With no annotations, the description carries the full behavioral load and does well: it discloses upsert semantics ('Omitted fields keep their current value'), the status lifecycle and automatic transitions (opening the period flips planned to active, close_period sets done, new milestones in an open quarter start active), and a validation rule (a new milestone needs a goal). It says nothing about permissions or failure modes when the year overview is missing, which is the remaining gap.

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 the when-to-use sentence followed by the one-line definition, then parameter detail — a sensible order. There is mild redundancy between the trigger sentence and 'Create or update a quarterly milestone', but the status-lifecycle parenthetical is dense, useful information rather than padding.

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 5-parameter mutation tool with no annotations and no output schema, the description covers nearly everything an agent needs: intent, upsert defaults, lifecycle side effects, and most parameter formats. The unexplained required `key` parameter is the one substantive hole.

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 0%, so the description must compensate and largely does: it defines year format (YYYY with an existing overview), quarter values (Q1-Q4), goal format (one line, user's language, required for creation) and the status enum (planned | active | done) with its transition rules. However, the required `key` parameter is never explained, leaving an agent to guess its meaning and format.

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 verb and resource — 'Create or update a quarterly milestone — a year's goal for one quarter' — and the leading trigger sentence anchors it to the user intent ('sets or changes a quarter's goal'). It is clearly distinguishable from siblings like open_period and close_period, which only affect the milestone's status.

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 an explicit usage trigger ('when the user sets or changes a quarter's goal') plus a when-not/optionality note ('A milestone is optional — tasks never need one') and a prerequisite ('its overview must exist'). It stops short of naming an alternative tool for the goal-setting case, but no sibling actually competes for that job.

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