architect_sdd_extract

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation profile is partly covered; the description usefully adds that the write target is a specific file. It does not say whether an existing harvest.json is overwritten, merged, or appended, nor what the 'audit' mode changes — the gaps that matter most given idempotentHint=false.

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?

One sentence, front-loaded with the verb and the deliverable path, with the parameter hint folded in rather than padded. Nothing wasted, though the single-sentence form leaves no room for the missing behavioral details.

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 non-idempotent write tool with no output schema and a 33%-documented schema, the description omits overwrite semantics, the meaning of 'audit', and any relationship to the surrounding SDD pipeline. The result file's structure is only hinted at through a list of categories.

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 33%, so the description must carry the load, and it does not. It explains the 'sources' omission behavior but leaves 'audit' (what does auditing add?) and the expected shape/format of sources entries undocumented in both places.

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 ('Extract') and enumerates the resource categories (requirements, ADRs, scenarios, conflict records) plus the exact output artifact path '.architect-build/harvest.json'. It never names a sibling, so an agent cannot tell from the text alone why this differs from architect_sdd_read or architect_sdd_prepare_check.

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 parenthetical 'auto-discovers sources when omitted' implies when the sources parameter can be skipped, which is real usage guidance. But there is no statement of when to choose this over architect_sdd_read or architect_sdd_prepare_check, and no prerequisites (e.g., sdd-workspace.yml must exist, likely via architect_sdd_init).

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