project_docs_append

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

Annotations already declare a non-read-only, non-destructive, non-idempotent, closed-world operation; the description adds real value beyond that by disclosing the two side effects (creating the record file and editing the family overview) and the boundary condition that the family root index is not touched. It also correctly conditions the overview link on the file existing. It stops short of saying what happens if a record with the same title/date already exists or whether the link step is skipped silently.

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 core action and destinations, and the semicolon-separated clauses each carry distinct information (path mapping, overview linking, root-index exclusion, usage gate). The first sentence is long and clause-heavy, which slightly hurts scanability, but nothing is redundant.

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 14-parameter write tool with no output schema, the definition covers purpose, destinations, and the usage gate, but says nothing about the return value (e.g., created path or link status), which the agent needs to confirm success. It also leaves the overwrite/collision behavior undefined, so an agent calling it twice cannot predict the outcome.

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 93%, so baseline is 3. The description does add a mapping the schema lacks: kind=caution routes to .issueops/cautions/ and kind=adr routes to .issueops/adr/, which tells the agent what kind actually controls. Beyond that it adds no meaning to the other 13 parameters (evidence, alternatives, authority_file, etc.), which the schema already documents well.

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 ('Append one dated record file') plus the exact destination directories keyed by kind, so an agent knows precisely what gets created and where. The write-and-link behavior is unambiguous and clearly separable from the read/revise/route siblings in the project_docs family.

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 gate: 'Use only when there is a concrete issue resolved or decision made,' which excludes speculative or in-progress notes. It also warns that the tool writes files. However, it never names the alternative tool to use when that condition is not met (e.g., project_docs_revise or project_docs_read), leaving routing to inference.

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