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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the replace semantics are partly covered. The description still adds real value beyond the annotations: the 512KB cap on the encoded request body and the read-first/merge workflow, which tells the agent this is a whole-context overwrite rather than an incremental append. It does not detail the response or failure behavior.

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 constraint, then the operational workflow, then the inclusion/exclusion guidance. Information-dense with essentially no filler, though the middle sentence packs several clauses into a run-on that could be broken up for readability.

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 destructive write tool with no output schema, the description covers the safety profile (via annotations), the size limit, the read-merge-save workflow, and detailed content inclusion/exclusion rules. An agent has everything needed to call it correctly and safely.

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 baseline is 3. The description goes further by explaining the semantic intent of the fields - what qualifies as 'durable product truth' for goals, activation events, glossary entries, and annotations, and which events are meaningful for annotations. This adds interpretation the schema does not.

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 ('set or replace') and resource ('compact project context'), and the instruction to 'read existing context first' implicitly distinguishes it from the read counterpart get_project_context. An agent can identify both what it does and how it differs from the sibling read tool.

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 explicit when-to-use guidance (save only durable product truth tied to goals, activation events, glossary, date annotations; use annotations for landing page/pricing/onboarding/feature/release/experiment changes) and explicit when-not (no git commit logs, noisy edits, PII, secrets, or long release notes). It also prescribes a read-merge-save workflow. Nothing is left to inference.

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