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

Goes beyond the annotations by disclosing that same kind+name+connection replaces the prior definition, that remove: true deletes, and that every save is versioned — real mutation semantics that the destructiveHint flag alone doesn't convey. It stops short of saying whether prior versions are recoverable or what permissions are needed.

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 and dense with useful content, but the connectionId sentence ('where it takes the place of one of its kind and name that holds for all') is a convoluted run-on that an agent may misparse. The kind-payload clauses are packed into one long parenthetical rather than structured per kind.

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 16 parameters and no output schema, the description covers the operation's core semantics and the discriminating fields. It leaves grain, synonyms, description and instructions unaddressed, which an agent filling in a dataset definition will need.

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 only 19%, and the description compensates well for the important fields: it explains the kind enum by giving the payload each kind expects (metric expression, dataset table/fields/isTime/primaryKey, relationship from/to/fromColumns/toColumns) and the connectionId scoping rule. Several parameters remain undocumented in both places — grain, synonyms, description, instructions — so it is not complete.

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 concrete verb and resource ('Save or remove one shared definition') and explains the effect ('every teammate's Claude and Fastero's assistant use it'), which is far more than a name restatement. It does not name the counterpart reader tool (fastero_get_definitions) to differentiate, which keeps it short of a 5.

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?

'Save a definition when the user confirms what a number means, not on a guess' is an explicit trigger with an exclusion. It also gives a rule for when to supply connectionId versus omitting it. What's missing is how to handle an existing definition the agent wants to change rather than replace by name.

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