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

Annotations supply a safety profile (readOnlyHint=false, destructiveHint=false), so the remaining burden is scope and side effects. The description discloses bulk-deletion capability ('all'), but says nothing about whether removals are undoable, what happens when ids don't match, or whether 'all' also wipes non-beat markers such as notes. Bulk deletion paired with destructiveHint=false is a tension the description never resolves, even though the sibling 'undo' tool might explain it.

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?

A single front-loaded sentence that states the action and then the three target selectors in a scannable order. No filler, no restatement of the title, and every clause carries operational information.

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 4-parameter, no-output-schema mutation tool this is the minimum viable: it establishes what can be deleted but leaves reversibility, precedence among selectors, and behavior on zero matches unspecified. Those gaps matter more here than for a read tool because the 'all' path can remove every marker in a project at once.

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 only 25% (just projectId documented), so the description must carry weight and largely does: it maps markerIds to 'by id', the kind enum to 'all beat markers', and 'all' to a full-clear flag. What remains unaddressed is precedence/interaction between the three selection parameters and the projectId scoping behavior, which the schema does cover but the description could reinforce.

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?

The description gives a specific verb+resource ('Remove markers') and enumerates the three ways targets can be selected: by id, by kind ('beat'), or all. This clearly separates it from add_marker, update_marker and list_markers in the sibling set. It stops short of explicitly naming an alternative when one operation should be preferred over another, but the purpose itself is unambiguous.

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 selection modes (ids, kind 'beat', or all) implicitly tell the agent which parameters to combine for each scenario, which is useful usage guidance. There is no explicit when-to-use/when-not-to-use framing, no statement that the modes are mutually exclusive or which one wins if several are supplied, and no pointer to siblings such as update_marker or undo when the intent is correction rather than deletion.

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