Record a meal manually or from a photo estimate, capturing calories and optional item details like name, grams, and kcal.
录入一餐(照片估算或手动)。items=[{name,grams,kcal}]
| Name | Required | Description | Default |
|---|---|---|---|
| ts | No | ||
| kcal | Yes | ||
| note | No | ||
| items | No | ||
| confidence | No | ||
| photo_path | No |
Changes observed during successful MCP inspections.
v0.3.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does not say whether logging is additive or overwrites an existing entry, whether timestamps default to now, what permissions are needed, or what happens when only kcal is supplied. For a write tool with zero annotation coverage this is a substantial 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?
Two compact clauses, front-loaded with the action, with the parameter hint appended. Nothing is padded, though the brevity edges toward under-specification rather than true economy.
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?
A 6-parameter mutation tool with no annotations, no output schema, and 0% schema description coverage gets only a single line of prose. An agent can guess the core intent but lacks the detail needed to populate confidence, ts, photo_path, or note 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 description coverage is 0% across 6 parameters, so the description must compensate. It only clarifies the shape of one parameter, items=[{name,grams,kcal}], and even that omits per-item types. ts, note, confidence, and photo_path remain undocumented in both the schema and the description.
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 names a specific verb+resource (录入一餐 / log a meal) and immediately distinguishes the two capture modes (photo estimate vs manual). It is clearly separable from siblings like log_workout or query_samples, though it never names an alternative explicitly.
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?
"照片估算或手动" implies the two invocation paths (pass photo_path vs enter items/kcal directly), which is useful implied usage. However there is no statement of when to prefer one over the other, no prerequisites, and no exclusions relative to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.