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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false) by disclosing that the baseline is measured server-side at creation and must not be passed or invented. It also explains the downstream progress-tracking behavior of each of the three measurement modes, which is critical context an agent cannot infer from schema or annotations.

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 rule and hierarchy, then examples. It is longer than average but nearly every sentence carries a decision the agent must make. The parenthetical about citation rate scoring is slightly verbose relative to its value.

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 mutation tool with no output schema and open-world behavior, the description covers the novel, non-obvious mechanics thoroughly (server-side baseline, three measurement modes). Some ancillary parameters and any post-creation behavior beyond progress tracking are left to the schema.

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 still adds substantial meaning: it explains the interaction between metric_key, manual_total, and the fallback to link_goal_issues, and the ai_citation_rate example clarifies target_value semantics. It does not, however, clarify several of the 14 parameters (tags, stage, priority, due_at).

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 the specific verb+resource (create a goal for a brand) and immediately constrains the hierarchy to exactly two levels (top-level or sub-goal via parent_id). It clearly distinguishes itself from siblings like update_goal, delete_goal, list_goals, and content_for_goal.

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 three worked examples function as explicit when-to-use guidance: use metric_key when a metric covers it, manual_total when no metric covers it, and neither when progress should track linked issues. It ends by telling the agent to pick whichever reflects the work, with the failure mode spelled out.

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