set_project_knowledge

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

Annotations already declare idempotentHint=true and destructiveHint=true, so the safety profile is partly covered. The description adds real value by spelling out the UPSERT behavior ('same key updates the existing entry'), which directly explains the otherwise alarming destructiveHint, and notes downstream visibility. It omits permission/auth requirements and size/rate limits.

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?

Three tight sentences, front-loaded with the core action and UPSERT rule, then usage, then the read counterpart. No filler or repetition of structured data.

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 9-param, 3-required write tool with a fully covered schema and no output schema, the description covers purpose, mutation semantics, and usage adequately. The remaining unaddressed details (auto-injection via attach_context, tags/category behavior) are already handled in the schema, leaving little for the description to add.

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 100%, so the schema already documents key patterns, tag/filter usage, defaults, and threading params thoroughly. The description only echoes the key-based UPSERT concept and adds no parameter detail beyond the schema, so baseline 3 applies.

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 ('Write a structured fact to project knowledge') and immediately clarifies the UPSERT-by-key semantics. It names the sibling used for reading ('visible via get_project_knowledge'), letting an agent distinguish it from read/list tools without opening the schema.

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 concrete use cases ('deploy URLs, stack conventions, gotchas') and confirms the read counterpart, which is clear context for when to reach for it. It does not, however, contrast against the closely related 'remember' sibling or state exclusions, so guidance stops short of full when/when-not routing.

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